Daily Papers

Video generative models are increasingly used as world models for robotics, where a model generates a future visual rollout conditioned on the current observation and task instruction, and an inverse dynamics model (IDM) converts the generated frames into executable robot actions. However, current video world models lack explicit executability constraints. As a result, visually coherent rollouts may still violate rigid-body and kinematic consistency, producing unstable or infeasible control commands when decoded by an IDM. We refer to this mismatch between visual generation and physically executable control as the executability gap. While this gap can be mitigated at inference time using techniques such as rejection sampling, such approaches are inefficient due to the high cost of video generation. In this paper, we leverage the executability gap as a training signal and introduce Executable Video Alignment (EVA), a reinforcement-learning post-training framework for aligning video world models. EVA trains an inverse dynamics model on real robot trajectories and repurposes it as a reward model that evaluates generated videos through the action sequences they induce, encouraging smooth motions measured by velocity, acceleration, and jerk while penalizing actions that violate embodiment constraints. Importantly, the reward remains informative even when generated videos contain severe visual artifacts, since such artifacts typically translate into unstable or out-of-bound actions. Experiments on the RoboTwin benchmark and a real bimanual robot show that EVA reduces embodiment-specific artifacts in generated rollouts and improves downstream task execution success.

In situated collaboration, speakers often use intentionally underspecified deictic commands (e.g., ``pass me that''), whose referent becomes identifiable only by aligning speech with a brief co-speech pointing stroke. However, many embodied benchmarks admit language-only shortcuts, allowing MLLMs to perform well without learning the audio--visual alignment required by deictic interaction. To bridge this gap, we introduce Egocentric Co-Speech Grounding (EcoG), where grounding is executable only if an agent jointly predicts What, Where, and When. To operationalize this, we present EcoG-Bench, an evaluation-only bilingual (EN/ZH) diagnostic benchmark of 811 egocentric clips with dense spatial annotations and millisecond-level stroke supervision. It is organized under a Progressive Cognitive Evaluation protocol. Benchmarking state-of-the-art MLLMs reveals a severe executability gap: while human subjects achieve near-ceiling performance on EcoG-Bench (96.9\% strict Eco-Accuracy), the best native video-audio setting remains low (Gemini-3-Pro: 17.0\%). Moreover, in a diagnostic ablation, replacing the native video--audio interface with timestamped frame samples and externally verified ASR (with word-level timing) substantially improves the same model (17.0\%to42.9\%). Overall, EcoG-Bench provides a strict, executable testbed for event-level speech--gesture binding, and suggests that multimodal interfaces may bottleneck the observability of temporal alignment cues, independently of model reasoning.

Example-based guidance is widely used to improve mathematical reasoning at inference time, yet its effectiveness is highly unstable across problems and models-even when the guidance is correct and problem-relevant. We show that this instability arises from a previously underexplored gap between strategy usage-whether a reasoning strategy appears in successful solutions-and strategy executability-whether the strategy remains effective when instantiated as guidance for a target model. Through a controlled analysis of paired human-written and model-generated solutions, we identify a systematic dissociation between usage and executability: human- and model-derived strategies differ in structured, domain-dependent ways, leading to complementary strengths and consistent source-dependent reversals under guidance. Building on this diagnosis, we propose Selective Strategy Retrieval (SSR), a test-time framework that explicitly models executability by selectively retrieving and combining strategies using empirical, multi-route, source-aware signals. Across multiple mathematical reasoning benchmarks, SSR yields reliable and consistent improvements over direct solving, in-context learning, and single-source guidance, improving accuracy by up to +13 points on AIME25 and +5 points on Apex for compact reasoning models. Code and benchmark are publicly available at: https://github.com/lwd17/strategy-execute-pipeline.

Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning. SGI-Bench comprises over 1,000 expert-curated, cross-disciplinary samples inspired by Science's 125 Big Questions, enabling systematic evaluation of state-of-the-art LLMs. Results reveal gaps: low exact match (10--20%) in deep research despite step-level alignment; ideas lacking feasibility and detail; high code executability but low execution result accuracy in dry experiments; low sequence fidelity in wet protocols; and persistent multimodal comparative-reasoning challenges. We further introduce Test-Time Reinforcement Learning (TTRL), which optimizes retrieval-augmented novelty rewards at inference, enhancing hypothesis novelty without reference answer. Together, our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery.

Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable TikZ code. While TikZ is the de facto standard for scientific schematics due to its programmatic flexibility, its requirement for rigorous spatial precision presents a significant challenge for Multimodal Large Language Models. Progress is currently stifled by two primary gaps: (1) Data Quality Gap: existing image-TikZ corpora often lack strict executability and reliable visual alignment; (2) Evaluation Gap: a lack of benchmarks for both structural and visual fidelity. To address these, we present a closed-loop framework featuring: SciTikZ-230K, a large-scale, high-quality dataset from our Execution-Centric Data Engine covering 11 diverse scientific disciplines; SciTikZ-Bench, a multifaceted benchmark spanning from basic geometric constructs to intricate hierarchical schematics to evaluate both visual fidelity and structural logic. To further broaden the scope of visual-code optimization methodology, we introduce a novel Dual Self-Consistency Reinforcement Learning optimization paradigm, which utilizes Round-Trip Verification to penalize degenerate code and boost overall self-consistency. Empowered by these, our trained model SciTikZer-8B achieves state-of-the-art performance, consistently outperforming proprietary giants like Gemini-2.5-Pro and massive models like Qwen3-VL-235B-A22B-Instruct.

Vision-Language Models (VLMs) are increasingly pivotal for generalist robot manipulation, enabling tasks such as physical reasoning, policy generation, and failure detection. However, their proficiency in these high-level applications often assumes a deep understanding of low-level physical prerequisites, a capability that remains largely unverified. For robots to perform actions reliably, they must comprehend intrinsic object properties (e.g., material, weight), action affordances (e.g., graspable, stackable), and physical constraints (e.g., stability, reachability, or an object's state, such as being closed). Despite the widespread use of VLMs in manipulation tasks, we argue that off-the-shelf models may lack this granular, physically grounded understanding, as such prerequisites are often overlooked during training. To address this critical gap, we introduce PAC Bench, a comprehensive benchmark designed to systematically evaluate VLMs on their understanding of core Properties, Affordances, and Constraints (PAC) from a task executability perspective. PAC Bench features a diverse dataset with over 30,000 annotations, comprising 673 real-world images (115 object classes, 15 property types, and 1 to 3 affordances defined per class), 100 real-world humanoid-view scenarios, and 120 unique simulated constraint scenarios across four tasks. Our evaluations reveal significant gaps in the ability of current VLMs to grasp fundamental physical concepts, highlighting limitations in their suitability for reliable robot manipulation and pointing to key areas for targeted research. PAC Bench also serves as a standardized benchmark for rigorously evaluating physical reasoning in VLMs and guiding the development of more robust, physically grounded models for robotic applications. Project Page: https://pacbench.github.io/

FinanceQA is a testing suite that evaluates LLMs' performance on complex numerical financial analysis tasks that mirror real-world investment work. Despite recent advances, current LLMs fail to meet the strict accuracy requirements of financial institutions, with models failing approximately 60% of realistic tasks that mimic on-the-job analyses at hedge funds, private equity firms, investment banks, and other financial institutions. The primary challenges include hand-spreading metrics, adhering to standard accounting and corporate valuation conventions, and performing analysis under incomplete information - particularly in multi-step tasks requiring assumption generation. This performance gap highlights the disconnect between existing LLM capabilities and the demands of professional financial analysis that are inadequately tested by current testing architectures. Results show that higher-quality training data is needed to support such tasks, which we experiment with using OpenAI's fine-tuning API. FinanceQA is publicly released at [this https URL](https://huggingface.co/datasets/AfterQuery/FinanceQA).

Code executability plays a vital role in software debugging and testing (e.g., detecting runtime exceptions or assertion violations). However, code execution, especially partial or arbitrary code execution, is a non-trivial task due to missing definitions and complex third-party dependencies. To make partial code (such as code snippets posted on the web or code fragments deep inside complex software projects) executable, the existing study has proposed a machine learning model to predict the undefined element types and inject the pre-defined dummy values into execution. However, the performance of their tool is limited due to its simply designed dummy values and the inability to continue learning. In this paper, we design and implement a novel framework, named SelfPiCo (Self Guided Partial Code Executor), to dynamically guide partial code execution by incorporating the open-source LLM (i.e., Code Llama) within an interactive loop. Particularly, SelfPiCo leverages few-shot in-context learning and chain-of-thought reasoning to elicit human knowledge and logical reasoning based on fine-tuning the Code Llama model. SelfPiCo continuously learns from code execution results and refines its predictions step after step. Our evaluations demonstrate that SelfPiCo can execute 72.7% and 83.3% of all lines in the open-source code and Stack Overflow snippets, outperforming the most recent state-of-the-art Lexecutor by 37.9% and 33.5%, respectively. Moreover, SelfPiCo successfully detected 18 and 33 runtime type error issues by executing the partial code from eight GitHub software projects and 43 Stack Overflow posts, demonstrating the practical usage and potential application of our framework in practice.

Code completion has become an essential tool for daily software development. Existing evaluation benchmarks often employ static methods that do not fully capture the dynamic nature of real-world coding environments and face significant challenges, including limited context length, reliance on superficial evaluation metrics, and potential overfitting to training datasets. In this work, we introduce a novel framework for enhancing code completion in software development through the creation of a repository-level benchmark ExecRepoBench and the instruction corpora Repo-Instruct, aim at improving the functionality of open-source large language models (LLMs) in real-world coding scenarios that involve complex interdependencies across multiple files. ExecRepoBench includes 1.2K samples from active Python repositories. Plus, we present a multi-level grammar-based completion methodology conditioned on the abstract syntax tree to mask code fragments at various logical units (e.g. statements, expressions, and functions). Then, we fine-tune the open-source LLM with 7B parameters on Repo-Instruct to produce a strong code completion baseline model Qwen2.5-Coder-Instruct-C based on the open-source model. Qwen2.5-Coder-Instruct-C is rigorously evaluated against existing benchmarks, including MultiPL-E and ExecRepoBench, which consistently outperforms prior baselines across all programming languages. The deployment of can be used as a high-performance, local service for programming development\url{https://execrepobench.github.io/}.

Coding agents are increasingly used as iterative development partners, but most benchmarks still evaluate one specification followed by one final assessment. This leaves out a basic question: can an agent keep its own codebase working as requirements change? We introduce EvoCode-Bench, a benchmark of 26 stateful coding tasks and 227 evaluated rounds. Each task preserves the agent's workspace for 5-15 rounds, states requirements through observable behavior, and uses cumulative executable tests to check new requirements and still-active prior ones. We evaluate 13 coding agents with two metrics: MT@4, a four-attempt fail-stop multi-round score, and SR, a single-round score from a reference-completed prior state. For most agents, SR exceeds MT@4 by 22-40 points. The gap also changes rankings: the highest-SR agent (78.9) ranks only third in persistent execution (44.0 MT@4). Even the strongest agents achieve only about 50% success on multi-turn metrics, and aggregate pass rate drops below half of round-1 performance by round 5. Failure analysis shows tier-dependent behavior: weaker agents fail early, while stronger agents survive long enough to expose specification-tracking and regression failures. We release the benchmark data and Harbor multi-turn infrastructure.

People overthink; language models over-sample, and the extra effort can talk both into a worse answer. Reasoning systems answer a hard question by sampling it many times (test-time scaling), and the more they draw, the more often a correct answer turns up somewhere, so coverage, the fraction of problems with at least one correct try, climbs and appears to be progress. But a deployed system must return one answer, and choosing it, not knowing which try is right, is selection; selection is capped, and past a point extra samples only make the model surer of a confident mistake, even as every draw adds cost. The gap between climbing coverage and stalled selection, the identifiability gap, is the answer a model can produce but not pick. So the real question is not whether to sample but how far, and the answer is: not far. For picking an answer, the vote has already settled within a few dozen draws, the modal ceiling; for scoring a benchmark, sooner still, the correlation ceiling. Beyond that, extra draws cost compute and add nothing, and can even make the answer worse. This paper turns the cutoff into a single number, the effective number of samples, that any sampling run already reveals. The bottleneck is recognizing a right answer, not generating one.

Code translation is a crucial activity in the software development and maintenance process, and researchers have recently begun to focus on using pre-trained large language models (LLMs) for code translation. However, existing LLMs only learn the contextual semantics of code during pre-training, neglecting executability information closely related to the execution state of the code, which results in unguaranteed code executability and unreliable automated code translation. To address this issue, we propose ExeCoder, an LLM specifically designed for code translation, aimed at utilizing executability representations such as functional semantics, syntax structures, and variable dependencies to enhance the capabilities of LLMs in code translation. To evaluate the effectiveness of ExeCoder, we manually enhanced the widely used benchmark TransCoder-test, resulting in a benchmark called TransCoder-test-X that serves LLMs. Evaluation of TransCoder-test-X indicates that ExeCoder achieves state-of-the-art performance in code translation, surpassing existing open-source code LLMs by over 10.88% to 38.78% and over 27.44% to 42.97% on two metrics, and even outperforms the renowned closed-source LLM GPT-4o. Website: https://execoder4trans.github.io/

OpenClaw-style agent stacks turn language into privileged execution: LLM intents flow through tool interception, policy gates, and a local executor. In parallel, skill marketplaces such as skills.sh make capability acquisition as easy as installing skills and CLIs, creating a growing capability supply chain. Together, these trends shift the dominant safety failure mode from "wrong answers" to execution-induced loss, where untrusted prompts, compromised skills, or narrative manipulation can trigger real trades and irreversible side effects. We propose Survivability-Aware Execution (SAE), an execution-layer survivability standard for OpenClaw-style systems and skill-enabled agents. SAE sits as middleware between a strategy engine (LLM or non-LLM) and the exchange executor. It defines an explicit execution contract (ExecutionRequest, ExecutionContext, ExecutionDecision) and enforces non-bypassable last-mile invariants: projection-based exposure budgets, cooldown and order-rate limits, slippage bounds, staged execution, and tool/venue allowlists. To make delegated execution testable under supply-chain risk, we operationalize the Delegation Gap (DG) via a logged Intended Policy Spec that enables deterministic out-of-scope labeling and reproducible DG metrics. On an offline replay using official Binance USD-M BTCUSDT/ETHUSDT perpetual data (15m; 2025-09-01--2025-12-01, incl. funding), SAE improves survivability: MDD drops from 0.4643 to 0.0319 (Full; 93.1%), |CVaR_0.99| shrinks from 4.025e-3 to ~1.02e-4 (~97.5%), and DG loss proxy falls from 0.647 to 0.019 (~97.0%). AttackSuccess decreases from 1.00 to 0.728 with zero FalseBlock in this run. Block bootstrap, paired Wilcoxon, and two-proportion tests confirm the shifts. SAE reframes agentic trading safety for the OpenClaw+skills era: treat upstream intent and skills as untrusted, and enforce survivability where actions become side effects.

We propose a framework for robust evaluation of reasoning capabilities of language models, using functional variants of benchmarks. Models that solve a reasoning test should exhibit no difference in performance over the static version of a problem compared to a snapshot of the functional variant. We have rewritten the relevant fragment of the MATH benchmark into its functional variant MATH(), with functionalization of other benchmarks to follow. When evaluating current state-of-the-art models over snapshots of MATH(), we find a reasoning gap -- the percentage difference between the static and functional accuracies. We find reasoning gaps from 58.35% to 80.31% among the state-of-the-art closed and open weights models that perform well on static benchmarks, with the caveat that the gaps are likely to be smaller with more sophisticated prompting strategies. Here we show that models which anecdotally have good reasoning performance over real-world tasks, have quantifiable lower gaps, motivating the open problem of building "gap 0" models. Code for evaluation and new evaluation datasets, three MATH() snapshots, are publicly available at https://github.com/consequentai/fneval/.

It is tempting to assume any task solvable by a short program can be taught to a model as its chain-of-thought: write the steps out, fine-tune, and the model follows. This paper shows the assumption fails for an identifiable class of procedures. The testbed is nine reasoning tasks, each from a deterministic generator; public and hidden splits share generators, so held-out data proxies test accuracy. I reverse-engineer the generators into Python solvers, render them as chain-of-thought, and distill into a rank-<= 32 LoRA over a 30B (3.5B-active) Nemotron model. Forward-computable tasks install readily: lookup/arithmetic and an 8-bit boolean task transfer (>= 0.99 and 0.68). Cryptarithm does not: distilling its backtracking search holds at 0.01-0.07 across eleven chain-of-thought designs, RL from verifiable rewards, and self-training, even though a search solver answers 71% of instances. This is not a capability gap. The model does the arithmetic on 97-100% of lines and ranks the correct cipher in its top eight on 71%; it cannot carry the search forward as a left-to-right derivation. Fine-tuning learns the shape of a verifiable elimination step while its verdicts become unconditional templates, correct only 16-57% of the time ("verdict-as-token"). The ceiling holds across backbones from 3B to 671B and across fine-tuning and prompting; a controlled intervention isolates the cause: revealing the cipher key, which turns the derivation forward, lifts the same instances from 0.03 to 0.57. When a procedure's only solution is search over information-free structure, no faithful forward chain-of-thought exists to imitate. The task becomes learnable only by removing the search, precomputing its combinatorial core into a catalog and reducing the trace to recall plus verification; the 1st-place solution reaches Private LB 0.92 this way. What distills is memorization and verification, not search.

In many real-world applications, deep neural networks are retrained from scratch as a dataset grows in size. Given the computational expense for retraining networks, it has been argued that continual learning could make updating networks more efficient. An obstacle to achieving this goal is the stability gap, which refers to an observation that when updating on new data, performance on previously learned data degrades before recovering. Addressing this problem would enable learning new data with fewer network updates, resulting in increased computational efficiency. We study how to mitigate the stability gap. We test a variety of hypotheses to understand why the stability gap occurs. This leads us to discover a method that vastly reduces this gap. In large-scale class incremental learning experiments, we are able to significantly reduce the number of network updates needed for continual learning. Our work has the potential to advance the state-of-the-art in continual learning for real-world applications along with reducing the carbon footprint required to maintain updated neural networks.

Current benchmarks for code agents primarily assess narrow, repository-specific fixes, overlooking critical real-world challenges such as cross-repository reasoning, domain-specialized problem solving, dependency-driven migration, and full-repository generation. To address this gap, we introduce BeyondSWE, a comprehensive benchmark that broadens existing evaluations along two axes - resolution scope and knowledge scope - using 500 real-world instances across four distinct settings. Experimental results reveal a significant capability gap: even frontier models plateau below 45% success, and no single model performs consistently across task types. To systematically investigate the role of external knowledge, we develop SearchSWE, a framework that integrates deep search with coding abilities. Our experiments show that search augmentation yields inconsistent gains and can in some cases degrade performance, highlighting the difficulty of emulating developer-like workflows that interleave search and reasoning during coding tasks. This work offers both a realistic, challenging evaluation benchmark and a flexible framework to advance research toward more capable code agents.

Evaluation harnesses are software systems that orchestrate model evaluation by managing model invocation, data loading, metric computation, and result reporting. Despite their critical role in machine learning infrastructure, their operational challenges and engineering concerns have received limited attention so far. We present an empirical study of 57 evaluation harnesses, deriving a five-stage harness model and classifying 16,560 issues by workflow stage and root cause. Most harness operational challenges concentrate in the Specification stage (41.4% of issues), where harnesses integrate external models, datasets, and scoring judges. The three most frequent root causes of operational challenges are unimplemented features (24.3%), documentation gaps (20.3%), and missing input validation (17.2%), which together account for 61.7% of classified issues, spanning both defects in existing functionality and capability gaps that block intended workflows. Root causes also vary by workflow stage: environment incompatibility and external dependency breakage account for 36.2% of provisioning issues, whereas algorithmic error (25.9%) and validation gap (22.5%) dominate assessment issues. Together, these contributions establish an empirical foundation for treating evaluation engineering as a distinct software engineering concern.

Establishing fair and robust benchmarks is essential for evaluating intelligent code generation by large language models (LLMs). Our survey of 35 existing benchmarks uncovers three major imbalances: 85.7% focus on a single programming language; 94.3% target only function-level or statement-level tasks; and over 80% include fewer than ten test cases on average. To address these gaps, we propose MultiOOP, a multi-language object-oriented programming benchmark covering six popular languages (Python, PHP, C++, C#, Java, JavaScript) with 267 tasks per language. We design a translator that extends an existing single-language OOP benchmark and the pass@o metric to a multilingual setting. Moreover, we propose an automated framework for augmenting test cases to ensure the reliability of the evaluation results. We evaluate 14 mainstream LLMs under zero-shot prompting and report three key findings: 1) Substantial performance degradation: pass@1 scores on MultiOOP drop by up to 65.6 percentage points compared to function-level tasks (e.g., HumanEval). 2) Cross-language variability: GPT-4o mini achieves pass@1 of 48.06% in Python but only 0.12%-15.26% in other languages, indicating limited multilingual generalization. 3) Conceptual gaps: pass@o scores are consistently 1.1-19.2 points lower than pass@k, demonstrating that LLMs often generate executable code without fully capturing core OOP concepts. Our benchmark, metric extensions, and evaluation scripts will be publicly released to foster a more balanced and comprehensive assessment of LLMs in object-oriented code generation. Our code and data will be released at https://github.com/alphadl/OOP-eval and https://huggingface.co/datasets/codeai-dteam/MultiOOP respectively.

Efficient experiment reproduction is critical to accelerating progress in artificial intelligence. However, the inherent complexity of method design and training procedures presents substantial challenges for automation. Notably, reproducing experiments often requires implicit domain-specific knowledge not explicitly documented in the original papers. To address this, we introduce the paper lineage algorithm, which identifies and extracts implicit knowledge from the relevant references cited by the target paper. Building on this idea, we propose AutoReproduce, a multi-agent framework capable of automatically reproducing experiments described in research papers in an end-to-end manner. AutoReproduce enhances code executability by generating unit tests alongside the reproduction process. To evaluate the reproduction capability, we construct ReproduceBench, a benchmark annotated with verified implementations, and introduce novel evaluation metrics to assess both the reproduction and execution fidelity. Experimental results demonstrate that AutoReproduce outperforms the existing strong agent baselines on all five evaluation metrics by a peak margin of over 70%. In particular, compared to the official implementations, AutoReproduce achieves an average performance gap of 22.1% on 89.74% of the executable experiment runs. The code will be available at https://github.com/AI9Stars/AutoReproduce.

Security experts reverse engineer (decompile) binary code to identify critical security vulnerabilities. The limited access to source code in vital systems - such as firmware, drivers, and proprietary software used in Critical Infrastructures (CI) - makes this analysis even more crucial on the binary level. Even with available source code, a semantic gap persists after compilation between the source and the binary code executed by the processor. This gap may hinder the detection of vulnerabilities in source code. That being said, current research on Large Language Models (LLMs) overlooks the significance of decompiled binaries in this area by focusing solely on source code. In this work, we are the first to empirically uncover the substantial semantic limitations of state-of-the-art LLMs when it comes to analyzing vulnerabilities in decompiled binaries, largely due to the absence of relevant datasets. To bridge the gap, we introduce DeBinVul, a novel decompiled binary code vulnerability dataset. Our dataset is multi-architecture and multi-optimization, focusing on C/C++ due to their wide usage in CI and association with numerous vulnerabilities. Specifically, we curate 150,872 samples of vulnerable and non-vulnerable decompiled binary code for the task of (i) identifying; (ii) classifying; (iii) describing vulnerabilities; and (iv) recovering function names in the domain of decompiled binaries. Subsequently, we fine-tune state-of-the-art LLMs using DeBinVul and report on a performance increase of 19%, 24%, and 21% in the capabilities of CodeLlama, Llama3, and CodeGen2 respectively, in detecting binary code vulnerabilities. Additionally, using DeBinVul, we report a high performance of 80-90% on the vulnerability classification task. Furthermore, we report improved performance in function name recovery and vulnerability description tasks.

Software development is iterative, yet agentic coding benchmarks overwhelmingly evaluate single-shot solutions against complete specifications. Code can pass the test suite but become progressively harder to extend. Recent iterative benchmarks attempt to close this gap, but constrain the agent's design decisions too tightly to faithfully measure how code quality shapes future extensions. We introduce SlopCodeBench, a language-agnostic benchmark comprising 20 problems and 93 checkpoints, in which agents repeatedly extend their own prior solutions under evolving specifications that force architectural decisions without prescribing internal structure. We track two trajectory-level quality signals: verbosity, the fraction of redundant or duplicated code, and structural erosion, the share of complexity mass concentrated in high-complexity functions. No agent solves any problem end-to-end across 11 models; the highest checkpoint solve rate is 17.2%. Quality degrades steadily: erosion rises in 80% of trajectories and verbosity in 89.8%. Against 48 open-source Python repositories, agent code is 2.2x more verbose and markedly more eroded. Tracking 20 of those repositories over time shows that human code stays flat, while agent code deteriorates with each iteration. A prompt-intervention study shows that initial quality can be improved, but it does not halt degradation. These results demonstrate that pass-rate benchmarks systematically undermeasure extension robustness, and that current agents lack the design discipline iterative software development demands.

As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises in this setup, as the agent optimizes for passing tests while deviating from the users true goal. We study this reward hacking phenomenon by decompose software engineering tasks into three parts: (i) a natural language description of the specification (ii) visible validation tests that exercise specified features in isolation, and (iii) held-out tests that compose those same features to simulate real-world usage. Based on the specification and the visible validation test suites, a genuine agent would be able to generate a solution that can also pass all of the held-out tests. Therefore we use the gap in pass rates on these two suites to quantify reward hacking. Based on this methodology, we introduce SpecBench, a benchmark comprising 30 systems-level programming tasks ranging from short horizon tasks like building a JSON parser to ultra long horizon tasks like building an entire OS kernel from scratch. Large-scale experiments reveal a consistent pattern: while every frontier agent saturates the visible suite, reward hacking persists, with smaller models exhibiting larger gaps on holdout suites. The gap also scales sharply with task length: it grows by 28 percentage points for every tenfold increase in code size. Failures range from subtle feature isolation to deliberate exploits, including a 2,900-line hash-table "compiler" that memorizes test inputs. SpecBench offers a principled testbed for measuring whether coding agents build genuine working systems or merely game the test suites developers hand them.

Majority voting over multiple LLM attempts improves mathematical reasoning, but correlated errors limit the effective sample size. A natural fix is to assign different reasoning strategies to different voters. The approach, Diverse Prompt Mixer, is tested on the AIMO 3 competition: 3 models, 23+ experiments, 50 IMO-level problems, one H100 80 GB, 5-hour limit. Every prompt-level intervention fails. High-temperature sampling already decorrelates errors; weaker strategies reduce accuracy more than they reduce correlation. Across an 8-point capability gap at equal N=8 and every optimization tested, model capability dominates. The gap between the best majority-vote score (42/50) and pass@20 (~45.5) is selection loss, not prompt loss. A verifier-based selector could close it. Prompt engineering cannot.

Bug-fix benchmarks are fundamental in advancing various sub-fields of software engineering such as automatic program repair (APR) and fault localization (FL). A good benchmark must include recent examples that accurately reflect technologies and development practices of today. To be executable in the long term, a benchmark must feature test suites that do not degrade overtime due to, for example, dependencies that are no longer available. Existing benchmarks fail in meeting both criteria. For instance, Defects4J, one of the foremost Java benchmarks, last received an update in 2020. Moreover, full-reproducibility has been neglected by the majority of existing benchmarks. In this paper, we present GitBug-Actions: a novel tool for building bug-fix benchmarks with modern and fully-reproducible bug-fixes. GitBug-Actions relies on the most popular CI platform, GitHub Actions, to detect bug-fixes and smartly locally execute the CI pipeline in a controlled and reproducible environment. To the best of our knowledge, we are the first to rely on GitHub Actions to collect bug-fixes. To demonstrate our toolchain, we deploy GitBug-Actions to build a proof-of-concept Go bug-fix benchmark containing executable, fully-reproducible bug-fixes from different repositories. A video demonstrating GitBug-Actions is available at: https://youtu.be/aBWwa1sJYBs.

Frontier model progress is often measured by academic benchmarks, which offer a limited view of performance in real-world professional contexts. Existing evaluations often fail to assess open-ended, economically consequential tasks in high-stakes domains like Legal and Finance, where practical returns are paramount. To address this, we introduce Professional Reasoning Bench (PRBench), a realistic, open-ended, and difficult benchmark of real-world problems in Finance and Law. We open-source its 1,100 expert-authored tasks and 19,356 expert-curated criteria, making it, to our knowledge, the largest public, rubric-based benchmark for both legal and finance domains. We recruit 182 qualified professionals, holding JDs, CFAs, or 6+ years of experience, who contributed tasks inspired by their actual workflows. This process yields significant diversity, with tasks spanning 114 countries and 47 US jurisdictions. Our expert-curated rubrics are validated through a rigorous quality pipeline, including independent expert validation. Subsequent evaluation of 20 leading models reveals substantial room for improvement, with top scores of only 0.39 (Finance) and 0.37 (Legal) on our Hard subsets. We further catalog associated economic impacts of the prompts and analyze performance using human-annotated rubric categories. Our analysis shows that models with similar overall scores can diverge significantly on specific capabilities. Common failure modes include inaccurate judgments, a lack of process transparency and incomplete reasoning, highlighting critical gaps in their reliability for professional adoption.

Benchmarks are necessary for healthcare evaluation, but are not sufficient for predicting deployment performance. Our position is that the evaluation--deployment gap arises not because of poorly designed benchmarks, but from implicit assumptions about how users interact with models that cannot be surfaced from benchmarks alone. To make this precise, we propose a classification of assumptions into two categories: task, which can be tested from conversation data alone, and outcome, which requires outcome data and behavioral studies for testing. Critically, outcome assumptions depend on human behavior, something that even well-designed benchmarks cannot directly observe. To demonstrate the operationality of this framework, we retrospectively analyze a healthcare RCT as a case study and find that the gap naturally separates into task and outcome gaps of roughly equal size. To address this, we make two contributions: first, we propose BenchmarkCards, an artifact that documents assumptions, and second, we propose staged evaluation, a procedure that systematically tests assumptions and evaluates performance.

LLM-based agents for program repair are increasingly built on a "generate-run-revise" paradigm, iteratively executing tests to evaluate and refine patches. This execution-based approach has become standard practice in state-of-the-art systems. However, executions can be time-consuming and expensive, yet their impact on these agents remains underexplored. In this paper, we conduct a two-stage empirical study over execution behavior in LLM-based program repair. To characterize execution behavior at scale, we first analyze 7,745 agent traces from SWE-bench leaderboard submissions. Second, we evaluate 3,000 end-to-end repair attempts across 200 SWE-bench instances and three agents (Claude Code, Codex, and the open-source OpenCode) under four execution paradigms, which allows for a fine-grained comparison of performance and cost. Our analysis reveals three key observations: (1) Code execution is used across all agents and models analyzed, with an average of 8.8 test runs per task. Execution behavior varies substantially across agents and models, with frequency ranging from 2 to 19 per task, and late-stage executions consistently achieve higher success rates than early-stage ones. (2) Execution restrictions have little effect on repair success: on commercial agents with SOTA models the resolve-rate gap between Prohibited and Unrestricted is only 1.25 percentage points and not statistically significant, while Prohibited saves substantial token and wall-clock cost. (3) Execution benefit is concentrated rather than uniform. These patterns suggest that current agents apply execution indiscriminately, paying its cost on instances where it provides little benefit. Execution, therefore, should be treated as a resource with an explicit cost-benefit tradeoff, not a default capability.

Deployed language models must produce outputs that are both correct and format-compliant. We study this structured-output reliability gap using two mathematical benchmarks -- GSM8K and MATH -- as a controlled testbed: ground truth is unambiguous and the output contract is strict (JSON with required fields). We evaluate three 7-9B models under five prompting strategies and report output accuracy -- the joint event of mathematical correctness and valid JSON structure -- as the primary metric. A systematic format failure emerges: NAIVE prompting (no system prompt) achieves up to 85% task accuracy on GSM8K but 0% output accuracy across all models and datasets. REFERENCE prompting (a minimal hand-written JSON format prompt) fares little better, yielding 0% output accuracy for two of four models tested. Constrained decoding enforces syntactic validity but incurs 3.6x-8.2x latency overhead and in several settings degrades task performance substantially. To overcome this limitation, we developed AloLab, an iterative system-prompt optimizer (meta-agent: Claude Sonnet 4.5) requiring only black-box API access to the target model; it reaches 84-87% output accuracy on GSM8K and 34-40% on MATH across five independent runs per model, with 29/30 paired McNemar comparisons against the best static prompt significant at p < 0.05, at near-NAIVE inference latency and without model fine-tuning. The same format failure extends to GPT-4o (OpenAI, 2024), a proprietary closed-source model: REFERENCE achieves 0% output accuracy due to systematic markdown-fence wrapping, while AloLab reaches 95.2% [94.8, 95.6]. An ablation replacing the Sonnet 4.5 meta-agent with Claude 3 Haiku reduces mean output accuracy to 61.0% and increases run-to-run standard deviation from <1 pp to 21.8 pp, confirming that meta-agent capability is a primary driver of optimization quality.

Test-time scaling has enabled Large Language Models (LLMs) with remarkable reasoning capabilities, particularly in mathematical domains, through intermediate chain-of-thought (CoT) reasoning before generating final answers. However, the specific sources and mechanisms underlying these reasoning capabilities remain insufficiently understood. Optimization reasoning, i.e. finding extrema under constraints, represents a fundamental abstraction that underpins critical applications in planning, control, resource allocation, and prompt search. To systematically evaluate this capability, we introduce ExtremBench, a benchmark dataset for solving mathematical extremal problems, curated from inequality exercises used for Chinese Mathematical Olympiad and transformed into 93 standardized extrema-finding problems. We conduct extensive evaluations across various state-of-the-art open-source model families, including the Qwen3, GPT-OSS, and DeepSeek. Our results reveal that LLMs' extremal-solving reasoning capabilities do not always align with those of current mathematical benchmarks such as AIME25 and MATH-500, with some models showing strong general mathematical reasoning but poor extremal-solving skills, and vice versa. This discrepancy highlights a critical gap in current evaluation practices and suggests that existing benchmarks may not comprehensively capture the full spectrum of mathematical reasoning abilities.

LLMs have become the go-to choice for code generation tasks, with an exponential increase in the training, development, and usage of LLMs specifically for code generation. To evaluate the ability of LLMs on code, both academic and industry practitioners rely on popular handcrafted benchmarks. However, prior benchmarks contain only a very limited set of problems, both in quantity and variety. Further, due to popularity and age, many benchmarks are prone to data leakage where example solutions can be readily found on the web and thus potentially in training data. Such limitations inevitably lead us to inquire: Is the leaderboard performance on existing benchmarks reliable and comprehensive enough to measure the program synthesis ability of LLMs? To address this, we introduce EvoEval -- a program synthesis benchmark suite created by evolving existing benchmarks into different targeted domains for a comprehensive evaluation of LLM coding abilities. Our study on 51 LLMs shows that compared to the high performance obtained on standard benchmarks like HumanEval, there is a significant drop in performance (on average 39.4%) when using EvoEval. Additionally, the decrease in performance can range from 19.6% to 47.7%, leading to drastic ranking changes amongst LLMs and showing potential overfitting of existing benchmarks. Furthermore, we showcase various insights, including the brittleness of instruction-following models when encountering rewording or subtle changes as well as the importance of learning problem composition and decomposition. EvoEval not only provides comprehensive benchmarks, but can be used to further evolve arbitrary problems to keep up with advances and the ever-changing landscape of LLMs for code. We have open-sourced our benchmarks, tools, and complete LLM generations at https://github.com/evo-eval/evoeval

Are AI agents tools, co-authors, or researchers? We present a quantified case study (N=1): a physicist supervising an AI coding agent (Claude Code, Sonnet and Opus models) over 12 work days and 57 sessions to build CLAX-PT, a differentiable one-loop perturbation theory module in JAX. We documented and classified 15 supervision events by intervention level. The agent resolved ten autonomously by iterating against oracle tests. Two more by the physicist's domain knowledge. The three it could not -- all evaded oracle detection -- share a common property: the agent treated symptom reduction as root-cause resolution. It spent 33 of the 57 sessions adjusting coefficients within a code architecture that could not represent the target physics, and could not re-evaluate its CLASS-PT branch choice even when prompted to reconsider; only an injected physics concept (anisotropic BAO damping) triggered the redesign. Separately, the agent committed a calibrated correction that passed all oracle tests but corresponded to no quantity in the theory, predicting wrong values at any other cosmology. The fudge factor was caught and replaced within the same session. Three supervision practices proved critical for catching what oracle tests missed: testing at diverse parameter points beyond the fiducial calibration; shared changelogs that surfaced stalled exploration across sessions; and an explicit rule against unphysical numerical patches. In this case, supervision design, not model capability, determined whether the agent's output was trustworthy. Closing the gap would require agents that propose architectural alternatives rather than optimize within a given structure, and distinguish predictive adequacy from explanatory correctness -- capabilities not exhibited here, not obviously addressed by scaling alone. [Abridged.]

Programming assistants powered by large language models have transformed software development, yet most benchmarks focus narrowly on code generation tasks. Recent efforts like InfiBench and StackEval attempt to address this gap using Stack Overflow data but remain limited to single-turn interactions in isolated contexts, require significant manual curation, and fail to represent complete project environments. We introduce CodeAssistBench (CAB), the first benchmark framework for evaluating multi-turn programming assistance in realistic settings that address real-world questions about actual codebases. Unlike existing programming Q&A benchmarks, CAB automatically generates scalable datasets from question-related GitHub issues using configurable parameters (e.g., repository creation date, star count, programming languages), and includes automatic containerization of codebases for evaluation. It then evaluates models through simulated users in these containerized environments with full codebase access. Using this framework, we constructed a test set of 3,286 real-world programming questions across 231 repositories, spanning seven programming languages and diverse problem domains. Our evaluation of leading LLMs reveals a substantial capability gap: while models perform well on Stack Overflow questions with success rates of 70-83%, they resolve only up to 16.49% of CAB's recent issues. This discrepancy highlights the challenges of providing assistance in complex, project-specific contexts versus answering standalone questions.

Background: Deep learning models are typically trained using stochastic gradient descent or one of its variants. These methods update the weights using their gradient, estimated from a small fraction of the training data. It has been observed that when using large batch sizes there is a persistent degradation in generalization performance - known as the "generalization gap" phenomena. Identifying the origin of this gap and closing it had remained an open problem. Contributions: We examine the initial high learning rate training phase. We find that the weight distance from its initialization grows logarithmically with the number of weight updates. We therefore propose a "random walk on random landscape" statistical model which is known to exhibit similar "ultra-slow" diffusion behavior. Following this hypothesis we conducted experiments to show empirically that the "generalization gap" stems from the relatively small number of updates rather than the batch size, and can be completely eliminated by adapting the training regime used. We further investigate different techniques to train models in the large-batch regime and present a novel algorithm named "Ghost Batch Normalization" which enables significant decrease in the generalization gap without increasing the number of updates. To validate our findings we conduct several additional experiments on MNIST, CIFAR-10, CIFAR-100 and ImageNet. Finally, we reassess common practices and beliefs concerning training of deep models and suggest they may not be optimal to achieve good generalization.

Large Language Models (LLMs) have demonstrated exceptional coding capability. However, as another critical component of programming proficiency, the debugging capability of LLMs remains relatively unexplored. Previous evaluations of LLMs' debugging ability are significantly limited by the risk of data leakage, the scale of the dataset, and the variety of tested bugs. To overcome these deficiencies, we introduce `DebugBench', an LLM debugging benchmark consisting of 4,253 instances. It covers four major bug categories and 18 minor types in C++, Java, and Python. To construct DebugBench, we collect code snippets from the LeetCode community, implant bugs into source data with GPT-4, and assure rigorous quality checks. We evaluate two commercial and three open-source models in a zero-shot scenario. We find that (1) while closed-source models like GPT-4 exhibit inferior debugging performance compared to humans, open-source models such as Code Llama fail to attain any pass rate scores; (2) the complexity of debugging notably fluctuates depending on the bug category; (3) incorporating runtime feedback has a clear impact on debugging performance which is not always helpful. As an extension, we also compare LLM debugging and code generation, revealing a strong correlation between them for closed-source models. These findings will benefit the development of LLMs in debugging.

Many popular programming languages, including C#, Java, and Python, support exceptions. Exceptions are thrown during program execution if an unwanted event happens, e.g., a method is invoked with an illegal argument value. Software developers write exceptional behavior tests (EBTs) to check that their code detects unwanted events and throws appropriate exceptions. Prior research studies have shown the importance of EBTs, but those studies also highlighted that developers put most of their efforts on "happy paths", e.g., paths without unwanted events. To help developers fill the gap, we present the first framework, dubbed exLong, that automatically generates EBTs. exLong is a large language model instruction-tuned from CodeLlama and embeds reasoning about traces that lead to throw statements, conditional expressions that guard throw statements, and non-exceptional behavior tests that execute similar traces. We compare exLong with the state-of-the-art models for test generation (CAT-LM) and one of the strongest foundation models (GPT3.5), as well as with analysis-based tools for test generation (Randoop and EvoSuite). Our results show that exLong outperforms existing models and tools. Furthermore, we contributed several pull requests to open-source projects and 23 EBTs generated by exLong were already accepted.

Large Language Models (LLMs) have demonstrated remarkable performance on coding related tasks, particularly on assisting humans in programming and facilitating programming automation. However, existing benchmarks for evaluating the code understanding and generation capacities of LLMs suffer from severe limitations. First, most benchmarks are deficient as they focus on a narrow range of popular programming languages and specific tasks, whereas the real-world software development scenarios show dire need to implement systems with multilingual programming environments to satisfy diverse requirements. Practical programming practices also strongly expect multi-task settings for testing coding capabilities of LLMs comprehensively and robustly. Second, most benchmarks also fail to consider the actual executability and the consistency of execution results of the generated code. To bridge these gaps between existing benchmarks and expectations from practical applications, we introduce CodeScope, an execution-based, multilingual, multi-task, multi-dimensional evaluation benchmark for comprehensively gauging LLM capabilities on coding tasks. CodeScope covers 43 programming languages and 8 coding tasks. It evaluates the coding performance of LLMs from three dimensions (perspectives): difficulty, efficiency, and length. To facilitate execution-based evaluations of code generation, we develop MultiCodeEngine, an automated code execution engine that supports 14 programming languages. Finally, we systematically evaluate and analyze 8 mainstream LLMs on CodeScope tasks and demonstrate the superior breadth and challenges of CodeScope for evaluating LLMs on code understanding and generation tasks compared to other benchmarks. The CodeScope benchmark and datasets are publicly available at https://github.com/WeixiangYAN/CodeScope.

We study the depth of grade-school math (GSM) problem-solving capabilities of LLMs. To this end, we evaluate their performance on pairs of existing math word problems together so that the answer to the second problem depends on correctly answering the first problem. Our findings reveal a significant reasoning gap in most LLMs, that is performance difference between solving the compositional pairs and solving each question independently. This gap is more pronounced in smaller, more cost-efficient, and math-specialized models. Moreover, instruction-tuning recipes and code generation have varying effects across LLM sizes, while finetuning on GSM can lead to task overfitting. Our analysis indicates that large reasoning gaps are not because of test-set leakage, but due to distraction from additional context and poor second-hop reasoning. Overall, LLMs exhibit systematic differences in their reasoning abilities, despite what their performance on standard benchmarks indicates.

Autonomous agents that address day-to-day digital tasks (e.g., ordering groceries for a household), must not only operate multiple apps (e.g., notes, messaging, shopping app) via APIs, but also generate rich code with complex control flow in an iterative manner based on their interaction with the environment. However, existing benchmarks for tool use are inadequate, as they only cover tasks that require a simple sequence of API calls. To remedy this gap, we built AppWorld Engine, a high-quality execution environment (60K lines of code) of 9 day-to-day apps operable via 457 APIs and populated with realistic digital activities simulating the lives of ~100 fictitious users. We then created AppWorld Benchmark (40K lines of code), a suite of 750 natural, diverse, and challenging autonomous agent tasks requiring rich and interactive code generation. It supports robust programmatic evaluation with state-based unit tests, allowing for different ways of completing a task while also checking for unexpected changes, i.e., collateral damage. The state-of-the-art LLM, GPT-4o, solves only ~49% of our 'normal' tasks and ~30% of 'challenge' tasks, while other models solve at least 16% fewer. This highlights the benchmark's difficulty and AppWorld's potential to push the frontiers of interactive coding agents. The project website is available at https://appworld.dev/.

While LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm, since certain risks can lead to severe consequences once carried out. However, existing guardrails mostly operate post-execution, which is difficult to scale and leaves little room for controllable supervision at the plan level. To address this challenge, we highlight three critical gaps in current research: data gap, model gap, and evaluation gap. To close the data gap, we introduce AuraGen, a controllable engine that (i) synthesizes benign trajectories, (ii) injects category-labeled risks with calibrated difficulty, and (iii) filters outputs via an automated reward model, producing large and reliable corpora for pre-execution safety. To close the guardian model gap, we propose a foundational guardrail Safiron, combining a cross-planner adapter with a compact guardian model. The adapter unifies different input formats, while Safiron flags risky cases, assigns risk types, and generates rationales; trained in two stages with a broadly explored data recipe, Safiron achieves robust transfer across settings. To close the evaluation gap, we release Pre-Exec Bench, a realistic benchmark covering diverse tools and branching trajectories, which measures detection, fine-grained categorization, explanation, and cross-planner generalization in human-verified scenarios. Extensive experiments demonstrate consistent gains of the proposed guardrail over strong baselines on Pre-Exec Bench, and ablations further distill actionable practices, providing a practical template for safer agentic systems.

Scaling up executable code data is significant for improving language models' software engineering capability. The intricate nature of the process makes it labor-intensive, time-consuming and expert-knowledge-dependent to build a large number of executable code repositories, limiting the scalability of existing work based on running tests. The primary bottleneck lies in the automated building of test environments for different repositories, which is an essential yet underexplored task. To mitigate the gap, we introduce Repo2Run, the first LLM-based agent aiming at automating the building of executable test environments for any repositories at scale. Specifically, given a code repository, Repo2Run iteratively builds the Docker image, runs unit tests based on the feedback of the building, and synthesizes the Dockerfile until the entire pipeline is executed successfully. The resulting Dockerfile can then be used to create Docker container environments for running code and tests. We created a benchmark containing 420 Python repositories with unit tests for evaluation. The results illustrate that Repo2Run achieves an 86.0% success rate, outperforming SWE-agent by 77.0%. The resources of Repo2Run are available at https://github.com/bytedance/Repo2Run.

Code LLMs still struggle with code execution reasoning, especially in smaller models. Existing methods rely on supervised fine-tuning (SFT) with teacher-generated explanations, primarily in two forms: (1) input-output (I/O) prediction chains and (2) natural-language descriptions of execution traces. However, intermediate execution steps cannot be explicitly verified during SFT, so the training objective can reduce to merely matching teacher explanations. Moreover, training data is typically collected without explicit control over task difficulty. We introduce ExecVerify, which goes beyond text imitation by incorporating verifiable white-box rewards derived from execution traces, including next-statement prediction and variable value/type prediction. Our work first builds a dataset with multiple difficulty levels via constraint-based program synthesis. Then, we apply reinforcement learning (RL) to reward correct answers about both intermediate execution steps and final outputs, aligning the training objective with semantic correctness at each execution step. Finally, we adopt a two-stage training pipeline that first enhances execution reasoning and then transfers to code generation. Experiments demonstrate that a 7B model trained with ExecVerify achieves performance comparable to 32B models on code reasoning benchmarks and improves pass@1 by up to 5.9\% on code generation tasks over strong post-training baselines.

Large language models (LLMs) have made remarkable progress in code generation, but competitive programming remains a challenge. Recent training-based methods have improved code generation by using reinforcement learning (RL) with execution feedback. The more recent framework CURE further incorporates test generation into the training process, jointly training a Coder and a Tester within a single model. At inference time, the Coder generates many candidate programs, and the Tester generates tests from the problem description. The candidate who passes the most of the generated tests is selected as the final answer. However, CURE has two critical limitations. First, the Tester never reads any candidate code, so its tests often fail to expose implementation-specific bugs. Second, the Coder generates every candidate from scratch and never learns to fix a buggy program based on a failed test. To address these limitations, we propose FixAudit, which approaches competitive code generation from a new perspective: starting from a single initial candidate, it iteratively improves the candidate through a targeted test-and-repair debugging cycle. The framework trains one shared model with two specialized roles through four stages: the Fixer, which repairs the current candidate based on a failing test, and the Auditor, which reads the candidate code to generate new tests that expose its remaining bugs. We evaluate FixAudit on three benchmarks: APPS, CodeContests, and xCodeEval. Applied to a 7B model, the framework surpasses the average performance of the larger 32B baseline within the same model family under the zero-shot setting. Compared to strong baselines built on the same 7B base model, FixAudit improves average Pass@1 by 35.1% to 36.8% and average AvgPassRatio by 7.1% to 24.5%.

The issue localization task aims to identify the locations in a software repository that requires modification given a natural language issue description. This task is fundamental yet challenging in automated software engineering due to the semantic gap between issue description and source code implementation. This gap manifests as two mismatches:(1) symptom-to-cause mismatches, where descriptions do not explicitly reveal underlying root causes; (2) one-to-many mismatches, where a single issue corresponds to multiple interdependent code entities. To address these two mismatches, we propose GraphLocator, an approach that mitigates symptom-to-cause mismatches through causal structure discovering and resolves one-to-many mismatches via dynamic issue disentangling. The key artifact is the causal issue graph (CIG), in which vertices represent discovered sub-issues along with their associated code entities, and edges encode the causal dependencies between them. The workflow of GraphLocator consists of two phases: symptom vertices locating and dynamic CIG discovering; it first identifies symptom locations on the repository graph, then dynamically expands the CIG by iteratively reasoning over neighboring vertices. Experiments on three real-world datasets demonstrates the effectiveness of GraphLocator: (1) Compared with baselines, GraphLocator achieves more accurate localization with average improvements of +19.49% in function-level recall and +11.89% in precision. (2) GraphLocator outperforms baselines on both symptom-to-cause and one-to-many mismatch scenarios, achieving recall improvement of +16.44% and +19.18%, precision improvement of +7.78% and +13.23%, respectively. (3) The CIG generated by GraphLocator yields the highest relative improvement, resulting in a 28.74% increase in performance on downstream resolving task.

Interactive agent benchmarks face a tension between scalable construction and realistic workflow evaluation. Hand-authored tasks are expensive to extend and revise, while static prompt evaluation misses failures that only appear when agents operate over persistent state. Existing interactive benchmarks have advanced agent evaluation significantly, but most initialize tasks from clean state and do not systematically test how agents handle pre-existing partial, stale, or conflicting artifacts. We present ClawForge, a generator-backed benchmark framework for executable command-line workflows under state conflict. The framework compiles scenario templates, grounded slots, initialized state, reference trajectories, and validators into reproducible task specifications, and evaluates agents step by step over persistent workflow surfaces using normalized end state and observable side effects rather than exact trajectory matching. We instantiate this framework as the ClawForge-Bench (17 scenarios, 6 ability categories). Results across seven frontier models show that the best model reaches only 45.3% strict accuracy, wrong-state replacement remains below 17\% for all models, and the widest model separation (17% to 90%) is driven by whether agents inspect existing state before acting. Partial-credit and step-efficiency analyses further reveal that many failures are near-miss closures rather than early breakdowns, and that models exhibit qualitatively different failure styles under state conflict.

Vision-language models (VLMs) generate fluent causal explanations, but current evaluations cannot distinguish linguistic plausibility from faithful causal reasoning. We introduce a dual-probe methodology that isolates these properties. The Text-Only Probe measures linguistic quality. The Chain-Text Probe requires models to first generate explicit causal chains. The Abstraction Gap (AG) metric quantifies the normalized performance difference. Evaluating eight VLMs on CAGE (Causal Abstraction Gap Evaluation), a benchmark of 49,500 questions across 5,500 images spanning Pearl's causal hierarchy, we find seven models exhibit AG exceeding 0.50 with text scores of 6--8 but chain scores below 2.5. Fine-tuning on 45,000 chain-annotated examples fails to close the gap. However, one model achieves near-zero AG. The capability exists within current VLM architectures and depends on pretraining and architectural choices. CAGE provides a diagnostic tool for assessing faithful causal reasoning in VLMs.

AI agents are increasingly expected to complete long-horizon workflows that require sustained progress over hours, millions of tokens, and complex environments. Yet current agent benchmarks largely evaluate short-form tasks, such as single pull requests, small tickets, or 5-10 minute exercises, limiting our ability to measure agents' capabilities in planning, long-context understanding, and memory use. We introduce SWE-Marathon, a benchmark of 20 long-horizon tasks spanning software engineering and adjacent technical domains. Each task consists of a unique executable environment, a human-written reference solution, and a multi-layer verification suite. Logged agent attempts average 27.2M total tokens, making SWE-Marathon substantially longer-horizon than existing SWE and command-line agent benchmarks. Current frontier coding agents solve fewer than 30% of tasks. Failures often arise from poor self-verification, self-reported infeasibility, and premature termination. We also observe reward-hacking behavior in 13.8% of rollouts, where agents attempt to exploit the environment or verifier to bypass the intended workflow. SWE-Marathon includes adversarial review of test suites and execution environments, as well as multi-layer checks designed to prevent shortcut solutions. We release SWE-Marathon, evaluation code, and agent trajectories at https://swe-marathon.org/.

Machine learning systems in fraud detection, credit scoring, and clinical risk assessment operate under delayed ground truth: outcome labels arrive days to months after the decision they evaluate. During this blind period, governance evidence degrades through mechanisms that neither drift detection methods nor governance frameworks adequately address. This paper formalizes an evidence sufficiency model with four dimensions (completeness, freshness, reliability, representativeness) and a decision-readiness gate that quantifies how label latency degrades evidence quality. The model maps three drift types to dimension-specific degradation trajectories. A complementary proxy indicator framework comprising seven measurement categories estimates sufficiency degradation without labels, with explicit coverage mapping and characterized blind spots per drift type. Evaluation on the IEEE-CIS Fraud Detection dataset (~590K transactions) with controlled drift injection shows that composite proxy monitoring detects covariate and mixed drift with 100% detection rate, while concept drift without feature change remains undetected -- consistent with the theoretical impossibility of unsupervised detection when P(X) is unchanged. Blind period simulation confirms monotone sufficiency degradation, with concept drift degrading fastest (S=0.242 at day 60 vs 0.418 for no-drift). The framework contributes a governance sufficiency monitoring instrument; its value lies in translating drift signals into auditable sufficiency assessments with characterized blind spots. Mapping sufficiency levels to governance actions requires deployment-specific calibration beyond this study's scope.

We introduce the first version of KWBench (Knowledge Work Bench), a benchmark for unprompted problem recognition in large language models: can an LLM identify a professional scenario before attempting to solve it. Existing frontier benchmarks have saturated, and most knowledge-work evaluations to date reduce to extraction or task completion against a specification. KWBench targets the step before that: recognizing the governing structure of the situation from raw inputs alone. The benchmark contains 223 tasks sourced from practitioners across acquisitions, contract negotiations, clinical pharmacy, organizational politics, fraud analysis, and incentive design. Each task encodes a formal game-theoretic pattern (principal-agent conflict, signaling, mechanism design failure, strategic omission, coalitional dynamics, strategic interdependence) and carries structured ground truth recording the expert reading of the situation and the anticipated failure modes. Models receive raw data and a task prompt with no indication of problem type. Scoring is a three-tier rubric gated by a mandatory conjunctive check. Mandatory criteria encode the predicted wrong paths. We evaluate 16 models. The best model passes on 27.9% of tasks. The top two models agree on only 31.7% of their passes. Among the top 8, 44 tasks are solved by exactly one model; routing across the top 8 covers 50.7% of the benchmark, nearly double the best single model. Conditional on passing, quality scores converge (approx 83% across models); unconditional scores do not. Same models articulate the relevant game-theoretic concept correctly when asked, then fail to apply it unprompted. We release KWBench to shift how frontier models are evaluated on knowledge work, scoring them on whether they recognize the right problem from the situation alone, not only on how well they execute once the problem has been framed for them.

Benchmarks are widely used to evaluate task completion by Large Language Models (LLMs), but this approach has accumulated construction-validity problems, and a passing score may not show whether the requested task was delivered. We study both problems. In a controlled code-as-spec setup, two production Copilot CLI agents (claude-opus-4.7, gpt-5.5) re-implement a React Fluent-UI data table in Angular as a reusable library under a hidden 222-test Playwright oracle across 18 runs and three oracle-availability conditions. Alongside the score, we run a mechanical library audit and check each verdict with a no-op ablation. Without the oracle, the library is present but unfinished, revealed by scores. With the oracle in the loop, the score reaches near-perfect, but from a demo holding the tested behavior directly, the library left dead or absent. We call this building to the test; the broader disposition behind both we call validation self-awareness. The agent does not, on its own, validate what it ships as a user would. Prevalence remains an open question across other agents, signals, and model families. Beyond benchmark scores, dispositions like validation self-awareness merit research attention.

Agentic systems increasingly solve complex user requests by executing orchestrated workflows, where subtasks are assigned to specialized models or tools and coordinated according to their dependencies. While recent work improves agent efficiency by optimizing the performance--cost--latency frontier, real deployments often impose concrete requirements: a workflow must be completed within a specified budget and before a specified deadline. This shifts the goal from average efficiency optimization to maximizing the probability that the entire workflow completes successfully under explicit budget and deadline constraints. We study constraint-driven online resource allocation for agentic workflows. Given a dependency-structured workflow and estimates of success rates and generation lengths for each subtask--model pair, the executor allocates models and parallel samples across simultaneously executable subtasks while managing the remaining budget and time. We formulate this setting as a finite-horizon stochastic online allocation problem and propose Monte Carlo Portfolio Planning (MCPP), a lightweight closed-loop planner that directly estimates constrained completion probability through simulated workflow executions and replans after observed outcomes. Experiments on CodeFlow and ProofFlow demonstrate that MCPP consistently improves constrained completion probability over strong baselines across a wide range of budget--deadline constraints.

We introduce WebApp1K, a novel benchmark for evaluating large language models (LLMs) in test-driven development (TDD) tasks, where test cases serve as both prompt and verification for code generation. Unlike traditional approaches relying on natural language prompts, our benchmark emphasizes the ability of LLMs to interpret and implement functionality directly from test cases, reflecting real-world software development practices. Comprising 1000 diverse challenges across 20 application domains, the benchmark evaluates LLMs on their ability to generate compact, functional code under the constraints of context length and multi-feature complexity. Our findings highlight instruction following and in-context learning as critical capabilities for TDD success, surpassing the importance of general coding proficiency or pretraining knowledge. Through comprehensive evaluation of 19 frontier models, we reveal performance bottlenecks, such as instruction loss in long prompts, and provide a detailed error analysis spanning multiple root causes. This work underscores the practical value of TDD-specific benchmarks and lays the foundation for advancing LLM capabilities in rigorous, application-driven coding scenarios.

Code benchmarks such as HumanEval are widely adopted to evaluate the capabilities of Large Language Models (LLMs), providing insights into their strengths and weaknesses. However, current benchmarks primarily exercise LLMs' capability on common coding tasks (e.g., bubble sort, greatest common divisor), leaving domain-specific coding tasks (e.g., computation, system, cryptography) unexplored. To fill this gap, we propose a multi-domain code benchmark, DOMAINEVAL, designed to evaluate LLMs' coding capabilities thoroughly. Our pipeline works in a fully automated manner, enabling a push-bottom construction from code repositories into formatted subjects under study. Interesting findings are observed by evaluating 12 representative LLMs against DOMAINEVAL. We notice that LLMs are generally good at computation tasks while falling short on cryptography and system coding tasks. The performance gap can be as much as 68.94% (80.94% - 12.0%) in some LLMs. We also observe that generating more samples can increase the overall performance of LLMs, while the domain bias may even increase. The contributions of this study include a code generation benchmark dataset DOMAINEVAL, encompassing six popular domains, a fully automated pipeline for constructing code benchmarks, and an identification of the limitations of LLMs in code generation tasks based on their performance on DOMAINEVAL, providing directions for future research improvements. The leaderboard is available at https://domaineval.github.io/.

Continual pre-training has increasingly become the predominant approach for adapting Large Language Models (LLMs) to new domains. This process involves updating the pre-trained LLM with a corpus from a new domain, resulting in a shift in the training distribution. To study the behavior of LLMs during this shift, we measured the model's performance throughout the continual pre-training process. we observed a temporary performance drop at the beginning, followed by a recovery phase, a phenomenon known as the "stability gap," previously noted in vision models classifying new classes. To address this issue and enhance LLM performance within a fixed compute budget, we propose three effective strategies: (1) Continually pre-training the LLM on a subset with a proper size for multiple epochs, resulting in faster performance recovery than pre-training the LLM on a large corpus in a single epoch; (2) Pre-training the LLM only on high-quality sub-corpus, which rapidly boosts domain performance; and (3) Using a data mixture similar to the pre-training data to reduce distribution gap. We conduct various experiments on Llama-family models to validate the effectiveness of our strategies in both medical continual pre-training and instruction tuning. For example, our strategies improve the average medical task performance of the OpenLlama-3B model from 36.2% to 40.7% with only 40% of the original training budget and enhance the average general task performance without causing forgetting. Furthermore, we apply our strategies to the Llama-3-8B model. The resulting model, Llama-3-Physician, achieves the best medical performance among current open-source models, and performs comparably to or even better than GPT-4 on several medical benchmarks. We release our models at https://huggingface.co/YiDuo1999/Llama-3-Physician-8B-Instruct.

Competitive programming has emerged as a critical benchmark for evaluating the reasoning and coding capabilities of Large Language Models (LLMs). Despite impressive progress on existing benchmarks, we argue that current evaluations overstate model proficiency, masking a substantial gap between LLMs and elite human programmers. This gap arises from two key limitations: insufficient difficulty and scope of benchmark problems, and evaluation bias from low-quality test cases. To address these shortcomings, we present AetherCode, a new benchmark that draws problems from premier programming competitions such as IOI and ICPC, offering broader coverage and higher difficulty. AetherCode further incorporates comprehensive, expert-validated test suites built through a hybrid of automated generation and human curation, ensuring rigorous and reliable assessment. By combining challenging problem design with robust evaluation, AetherCode provides a more faithful measure of LLM capabilities and sets a new standard for future research in code reasoning.

Competitive programming problems increasingly serve as valuable benchmarks to evaluate the coding capabilities of large language models (LLMs) due to their complexity and ease of verification. Yet, current coding benchmarks face limitations such as lack of exceptionally challenging problems, insufficient test case coverage, reliance on online platform APIs that limit accessibility. To address these issues, we introduce LiveOIBench, a comprehensive benchmark featuring 403 expert-curated Olympiad-level competitive programming problems, each with an average of 60 expert-designed test cases. The problems are sourced directly from 72 official Informatics Olympiads in different regions conducted between 2023 and 2025. LiveOIBench distinguishes itself through four key features: (1) meticulously curated high-quality tasks with detailed subtask rubrics and extensive private test cases; (2) direct integration of elite contestant performance data to enable informative comparison against top-performing humans; (3) planned continuous, contamination-free updates from newly released Olympiad problems; and (4) a self-contained evaluation system facilitating offline and easy-to-reproduce assessments. Benchmarking 32 popular general-purpose and reasoning LLMs, we find that GPT-5 achieves a notable 81.76th percentile, a strong result that nonetheless falls short of top human contestant performance, who usually place above 90th. In contrast, among open-weight reasoning models, GPT-OSS-120B achieves only a 60th percentile, underscoring significant capability disparities from frontier closed models. Detailed analyses indicate that robust reasoning models prioritize precise problem analysis over excessive exploration, suggesting future models should emphasize structured analysis and minimize unnecessary exploration. All data, code, and leaderboard results will be made publicly available on our website.

Large language models have demonstrated remarkable capabilities, but their performance is heavily reliant on effective prompt engineering. Automatic prompt optimization (APO) methods are designed to automate this and can be broadly categorized into those targeting instructions (instruction optimization, IO) vs. those targeting exemplars (exemplar selection, ES). Despite their shared objective, these have evolved rather independently, with IO recently receiving more research attention. This paper seeks to bridge this gap by comprehensively comparing the performance of representative IO and ES techniques, both isolation and combination, on a diverse set of challenging tasks. Our findings reveal that intelligently reusing model-generated input-output pairs obtained from evaluating prompts on the validation set as exemplars consistently improves performance over IO methods but is currently under-investigated. We also find that despite the recent focus on IO, how we select exemplars can outweigh how we optimize instructions, with ES strategies as simple as random search outperforming state-of-the-art IO methods with seed instructions without any optimization. Moreover, we observe synergy between ES and IO, with optimal combinations surpassing individual contributions. We conclude that studying exemplar selection as a standalone method and its optimal combination with instruction optimization remains a crucial aspect of APO and deserves greater consideration in future research, even in the era of highly capable instruction-following models.

Code generation models have increasingly become integral to aiding software development, offering assistance in tasks such as code completion, debugging, and code translation. Although current research has thoroughly examined the correctness of code produced by code generation models, a vital aspect, i.e., the efficiency of the generated code, has often been neglected. This paper presents EffiBench, a benchmark with 1,000 efficiency-critical coding problems for assessing the efficiency of code generated by code generation models. EffiBench contains a diverse set of LeetCode coding problems. Each problem is paired with an executable human-written canonical solution. With EffiBench, we empirically examine the capability of 21 Large Language Models (13 open-sourced and 8 closed-sourced) in generating efficient code. The results demonstrate that GPT-4-turbo generates the most efficient code, significantly outperforming Palm-2-chat-bison, Claude-instant-1, Gemini-pro, GPT-4, and GPT-3.5. Nevertheless, its code efficiency is still worse than the efficiency of human-written canonical solutions. In particular, the average and worst execution time of GPT-4-turbo generated code is 1.69 and 45.49 times that of the canonical solutions.

Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack of fine-grained evaluation metrics, fail to rigorously evaluate the long-horizon planning and execution capabilities essential for realistic software engineering. To address these gaps, we introduce LongCLI-Bench, a comprehensive benchmark designed to evaluate agentic capabilities across long-horizon, realistic tasks. We curated 20 high-quality, long-horizon tasks from over 1,000 computer science assignments and real-world workflows, covering four engineering categories: from scratch, feature addition, bug fixing, and refactoring. We propose a dual-set testing protocol for LongCLI-Bench, which measures requirement fulfillment (fail-to-pass) and regression avoidance (pass-to-pass), and incorporates step-level scoring to pinpoint execution failures. Extensive experiments reveal that even state-of-the-art agents achieve pass rates below 20% in LongCLI-Bench. Step-level analysis further indicates that the majority of tasks stall at less than 30% completion, highlighting that critical failures often occur in the early stages. Although self-correction offers marginal gains, human-agent collaboration through plan injection and interactive guidance yields significantly higher improvements. These results highlight that future research must emphasize the development of synergistic human-agent workflows alongside advances in agents' planning and execution capabilities to overcome key challenges in long-horizon task performance.

LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain largely centered on static, isolated, and short-horizon benchmarks that fail to capture the dynamic complexity of real-world production workflows. As a result, benchmark performance may poorly reflect practical capability under realistic runtime environments involving long execution chains, tool interactions, dependency management, and iterative feedback loops. We thus present RAMP, a production-grounded infrastructure for assessing long-horizon software engineering agents. Built upon the YatCC integrated platform, RAMP provides a unified runtime assessment architecture through standardized orchestration and execution interfaces. RAMP introduces realistic compiler-construction workloads with serial dependencies and complex toolchain interactions, together with a staged recovery mechanism for analyzing execution behavior under partial workflow failure. The framework further incorporates utility-oriented multi-dimensional metrics that jointly evaluate outcome quality and process efficiency. We conduct runtime assessments across 15 mainstream models and observe substantial capability degradation that remains largely invisible to conventional isolated benchmarks. Task completion rates progressively collapse across serial workflows, dropping from 100% in the initial stage to only 20% in the final stage, while none of the evaluated models successfully completes the entire pipeline. Runtime analysis reveals systematic failure propagation and significant resource inefficiencies, with computational costs differing by up to three orders of magnitude among comparable models. These findings suggest RAMP advances agentic model evaluation toward continuous, runtime-observable, and production-grounded assessment.

While current Computer Use Agent (CUA) benchmarks measure task completion effectively, they provide limited assessment of enterprise deployment readiness, emphasizing functional correctness over the operational reliability required for production systems. We present UI-CUBE (UiPath Computer Use BEnchmark), a systematic benchmark comprising 226 tasks across two difficulty tiers designed to expose fundamental architectural limitations in current CUAs. Our evaluation covers simple UI interactions (136 tasks) and complex workflows including copy-paste tasks (50 tasks) and enterprise application scenarios (40 tasks), with systematic interface variation coverage, multi-resolution testing and automated validation of task success through the application state. Evaluation of five state-of-the-art models reveals a sharp capability cliff rather than gradual performance degradation. Simple UI interactions achieve 67-85% success rates (compared to 97.9% human performance), but complex workflows drop precipitously to 9-19%. Human evaluators with no prior application experience achieve only 61.2% on complex tasks despite near-perfect performance on simple tasks, establishing realistic performance ceilings. This discontinuous performance pattern -- where agents achieve 68-87% of human performance on simple tasks but only 15-32% on complex workflows -- indicates fundamental architectural limitations in memory management, hierarchical planning, and state coordination rather than incremental capability gaps addressable through better training or prompting. UI-CUBE functions as an enterprise-readiness diagnostic, revealing that while current CUAs can manipulate individual interface elements, they cannot yet function as reliable workflow automation tools. These findings provide architectural insights essential for developing production-ready CUAs capable of managing complex, multi-step enterprise processes.

Despite widespread deployment of Large Language Models, systematic evaluation of instruction-following capabilities remains challenging. While comprehensive benchmarks exist, focused assessments that quickly diagnose specific instruction adherence patterns are valuable. As newer models may be trained on existing benchmarks, novel evaluation approaches are needed to assess genuine capabilities rather than memorized performance. This paper presents a streamlined evaluation framework using twenty carefully designed prompts to assess LLM instruction-following across diverse task categories. We demonstrate this framework through a large-scale empirical study conducted on October 14, 2025, testing 256 verified working models from 331 available via OpenRouter. To ensure methodological rigor and prevent selection bias, we first verified each model's basic functionality before inclusion. Unlike large-scale benchmarks requiring extensive computational resources, our approach offers a practical diagnostic tool researchers and practitioners can readily apply. Our methodology builds upon verifiable instructions while introducing a compact test suite balancing comprehensiveness with efficiency. Each prompt targets distinct aspects of instruction following, including format compliance, content constraints, logical sequencing, and multi-step task execution. We evaluate models from major providers (OpenAI, Anthropic, Google, Meta, Mistral) and emerging implementations (Qwen, DeepSeek, community models), providing comparative performance analysis. Our findings reveal consistent failure modes and identify specific instruction types posing particular challenges. This work contributes both a practical evaluation tool and one of the most comprehensive empirical analyses of instruction-following capabilities across the contemporary LLM landscape.

Large Language Models (LLMs) have shown remarkable capabilities in natural language understanding and generation, yet their deployment in enterprise environments reveals a critical limitation: inconsistent adherence to custom instructions. This study presents a comprehensive evaluation of 13 leading LLMs across instruction compliance, response accuracy, and performance metrics in realworld RAG (Retrieval-Augmented Generation) scenarios. Through systematic testing with samples and enterprise-grade evaluation protocols, we demonstrate that instruction following varies dramatically across models, with Claude-Sonnet-4 and GPT-5 achieving the highest results. Our findings reveal the "instruction gap" - a fundamental challenge where models excel at general tasks but struggle with precise instruction adherence required for enterprise deployment. This work provides practical insights for organizations deploying LLM-powered solutions and establishes benchmarks for instruction-following capabilities across major model families.

Recent progress in autonomous code generation has fueled excitement around AI agents capable of accelerating scientific discovery by running experiments. However, there is currently no benchmark that evaluates whether such agents can implement scientific ideas when given varied amounts of code as a starting point, interpolating between reproduction (running code) and from-scratch replication (fully re-implementing and running code). We introduce AutoExperiment, a benchmark that evaluates AI agents' ability to implement and run machine learning experiments based on natural language descriptions in research papers. In each task, agents are given a research paper, a codebase with key functions masked out, and a command to run the experiment. The goal is to generate the missing code, execute the experiment in a sandboxed environment, and reproduce the results. AutoExperiment scales in difficulty by varying the number of missing functions n, ranging from partial reproduction to full replication. We evaluate state-of-the-art agents and find that performance degrades rapidly as n increases. Agents that can dynamically interact with the environment (e.g. to debug their code) can outperform agents in fixed "agentless" harnesses, and there exists a significant gap between single-shot and multi-trial success rates (Pass@1 vs. Pass@5), motivating verifier approaches to our benchmark. Our findings highlight critical challenges in long-horizon code generation, context retrieval, and autonomous experiment execution, establishing AutoExperiment as a new benchmark for evaluating progress in AI-driven scientific experimentation. Our data and code are open-sourced at https://github.com/j1mk1m/AutoExperiment .

While the evaluation of explanations is an important step towards trustworthy models, it needs to be done carefully, and the employed metrics need to be well-understood. Specifically model randomization testing is often overestimated and regarded as a sole criterion for selecting or discarding certain explanation methods. To address shortcomings of this test, we start by observing an experimental gap in the ranking of explanation methods between randomization-based sanity checks [1] and model output faithfulness measures (e.g. [25]). We identify limitations of model-randomization-based sanity checks for the purpose of evaluating explanations. Firstly, we show that uninformative attribution maps created with zero pixel-wise covariance easily achieve high scores in this type of checks. Secondly, we show that top-down model randomization preserves scales of forward pass activations with high probability. That is, channels with large activations have a high probility to contribute strongly to the output, even after randomization of the network on top of them. Hence, explanations after randomization can only be expected to differ to a certain extent. This explains the observed experimental gap. In summary, these results demonstrate the inadequacy of model-randomization-based sanity checks as a criterion to rank attribution methods.

Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development, commercial investment, and scientific discovery, unfold in long-horizon and partially observable scenarios where success hinges on sustained reasoning, planning, memory management, and tool use. Existing benchmarks rarely capture these long-horizon challenges, leaving a gap in systematic evaluation. To bridge this gap, we introduce UltraHorizon a novel benchmark that measures the foundational capabilities essential for complex real-world challenges. We use exploration as a unifying task across three distinct environments to validate these core competencies. Agents are designed in long-horizon discovery tasks where they must iteratively uncover hidden rules through sustained reasoning, planning, memory and tools management, and interaction with environments. Under the heaviest scale setting, trajectories average 200k+ tokens and 400+ tool calls, whereas in standard configurations they still exceed 35k tokens and involve more than 60 tool calls on average. Our extensive experiments reveal that LLM-agents consistently underperform in these settings, whereas human participants achieve higher scores, underscoring a persistent gap in agents' long-horizon abilities. We also observe that simple scaling fails in our task. To better illustrate the failure of agents, we conduct an in-depth analysis of collected trajectories. We identify eight types of errors and attribute them to two primary causes: in-context locking and functional fundamental capability gaps. https://github.com/StarDewXXX/UltraHorizon{Our code will be available here.}

Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or implementing a small feature. However, real-world software engineering is fundamentally a long-horizon endeavor: developers must interpret high-level requirements, plan coordinated changes across many files, and evolve codebases over multiple iterations while preserving existing functionality. We introduce SWE-EVO, a benchmark that evaluates agents on this long-horizon software evolution challenge. Constructed from release notes and version histories of seven mature open-source Python projects, Tool comprises 48 evolution tasks that require agents to implement multi-step modifications spanning an average of 21 files, validated against comprehensive test suites averaging 874 tests per instance. Experiments with state-of-the-art models reveal a striking capability gap: even GPT-5 with OpenHands achieves only a 21 percent resolution rate on Tool, compared to 65 percent on the single-issue SWE-Bench Verified. This demonstrates that current agents struggle with sustained, multi-file reasoning. We also propose Fix Rate, a fine-grained metric that captures partial progress toward solving these complex, long-horizon tasks.

Code completion is a prominent application of Large Language Models (LLMs) in software engineering. Due to the near real-time response requirements of this task, base models with small to medium-sized parameters are typically employed, supplemented by various optimization and post-training techniques. However, these optimization methods often have trade-offs, leading to a seesaw effect where performance improvements on certain datasets or metrics are accompanied by degradations on others -- sometimes even falling below the baseline model's performance. This paper proposes SynthCoder, a model that integrates leading industry practices to achieve state-of-the-art performance on the Fill-in-the-Middle (FIM) code completion task. In specific, we first construct a diverse dataset by combining Abstract Syntax Tree (AST) node extraction with heuristics that simulate developer behavior. Then we enrich our training corpus with cross-file contextual information using the BM25 algorithm and call graphs, enhancing the model's ability to perform code completion in both file-level and repository-level scenarios. As the last step, we employ a two-stage training process using the Seed-Coder-8B-Base as the base model. First, we fine-tune the model using Curriculum Learning technology. Following this, we perform alignment using Direct Preference Optimization (DPO) with preference pairs generated through Rejection Sampling. Experimental results demonstrate that our final model excels on mainstream repository-level code completion benchmarks, including aiXcoder, ExecRepoBench, CrossCodeEval, and CoLT. Furthermore, our carefully curated training set effectively mitigates the model's tendency to just repeat existing code, a common issue existing in various code completion models.

Large language models of code (Code-LLMs) have recently brought tremendous advances to code completion, a fundamental feature of programming assistance and code intelligence. However, most existing works ignore the possible presence of bugs in the code context for generation, which are inevitable in software development. Therefore, we introduce and study the buggy-code completion problem, inspired by the realistic scenario of real-time code suggestion where the code context contains potential bugs -- anti-patterns that can become bugs in the completed program. To systematically study the task, we introduce two datasets: one with synthetic bugs derived from semantics-altering operator changes (buggy-HumanEval) and one with realistic bugs derived from user submissions to coding problems (buggy-FixEval). We find that the presence of potential bugs significantly degrades the generation performance of the high-performing Code-LLMs. For instance, the passing rates of CodeGen-2B-mono on test cases of buggy-HumanEval drop more than 50% given a single potential bug in the context. Finally, we investigate several post-hoc methods for mitigating the adverse effect of potential bugs and find that there remains a large gap in post-mitigation performance.

Code efficiency is a fundamental aspect of software quality, yet how to harness large language models (LLMs) to optimize programs remains challenging. Prior approaches have sought for one-shot rewriting, retrieved exemplars, or prompt-based search, but they do not explicitly distill reusable optimization knowledge, which limits generalization beyond individual instances. In this paper, we present EffiSkill, a framework for code-efficiency optimization that builds a portable optimization toolbox for LLM-based agents. The key idea is to model recurring slow-to-fast transformations as reusable agent skills that capture both concrete transformation mechanisms and higher-level optimization strategies. EffiSkill adopts a two-stage design: Stage I mines Operator and Meta Skills from large-scale slow/fast program pairs to build a skill library; Stage II applies this library to unseen programs through execution-free diagnosis, skill retrieval, plan composition, and candidate generation, without runtime feedback. Results on EffiBench-X show that EffiSkill achieves higher optimization success rates, improving over the strongest baseline by 3.69 to 12.52 percentage points across model and language settings. These findings suggest that mechanism-level skill reuse provides a useful foundation for execution-free code optimization, and that the resulting skill library can serve as a reusable resource for broader agent workflows.

The global economy is entering the era of Agentic Commerce, where autonomous agents can discover services, negotiate prices, and transact value. However adoption towards agentic commerce faces a foundational trust gap: current systems are built for direct human interactions rather than agent-driven operations. It lacks core primitives across three critical stages of agentic transactions. First, Task Delegation lacks means to translate user intent into defined scopes, discover appropriate agents, and securely authorize actions. Second, Payment Settlement for tasks is processed before execution, lacking verifiable evidence to validate the agent's work. Third, Audit Mechanisms fail to capture the full transaction lifecycle, preventing clear accountability for disputes. While emerging standards address fragments of this trust gap, there still remains a critical need for a unified infrastructure that binds the entire transaction lifecycle. To resolve this gap, we introduce TessPay, a unified infrastructure that replaces implicit trust with a 'Verify-then-Pay' architecture. It is a two plane architecture separating control and verification from settlement. TessPay operationalizes trust across four distinct stages: Before execution, agents are anchored in a canonical registry and user intent is captured as verifiable mandates, enabling stakeholder accountability. During execution, funds are locked in escrow while the agent executes the task and generates cryptographic evidence (TLS Notary, TEE etc.) to support Proof of Task Execution (PoTE). At settlement, the system verifies this evidence and releases funds only when the PoTE satisfies verification predicates; modular rail adapters ensure this PoTE-gated escrow remains chain-agnostic across heterogeneous payment rails. After settlement, TessPay preserves a tamper-evident audit trail to enable clear accountability for dispute resolution.

Vericoding refers to the generation of formally verified code from rigorous specifications. Recent AI models show promise in vericoding, but a unified methodology for cross-paradigm evaluation is lacking. Existing benchmarks test only individual languages/tools (e.g., Dafny, Verus, and Lean) and each covers very different tasks, so the performance numbers are not directly comparable. We address this gap with AlgoVeri, a benchmark that evaluates vericoding of 77 classical algorithms in Dafny, Verus, and Lean. By enforcing identical functional contracts, AlgoVeri reveals critical capability gaps in verification systems. While frontier models achieve tractable success in Dafny (40.3% for Gemini-3 Flash), where high-level abstractions and SMT automation simplify the workflow, performance collapses under the systems-level memory constraints of Verus (24.7%) and the explicit proof construction required by Lean (7.8%). Beyond aggregate metrics, we uncover a sharp divergence in test-time compute dynamics: Gemini-3 effectively utilizes iterative repair to boost performance (e.g., tripling pass rates in Dafny), whereas GPT-OSS saturates early. Finally, our error analysis shows that language design affects the refinement trajectory: while Dafny allows models to focus on logical correctness, Verus and Lean trap models in persistent syntactic and semantic barriers. All data and evaluation code can be found at https://github.com/haoyuzhao123/algoveri.

Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject. The root cause is not functional incorrectness but a lack of organicity: generated code ignores project-specific conventions, duplicates functionality already provided by internal APIs, and violates implicit architectural constraints accumulated over years of development. Simply exposing an agent to the latest repository snapshot is not enough: the snapshot reveals the final state of the codebase, but not the repository-specific change patterns by which that state was reached. We introduce Learning to Commit, a framework that closes this gap through Online Repository Memory. Given a repository with a strict chronological split, the agent performs supervised contrastive reflection on earlier commits: it blindly attempts to resolve each historical issue, compares its prediction against the oracle diff, and distils the gap into a continuously growing set of skills-reusable patterns capturing coding style, internal API usage, and architectural invariants. When a new PR description arrives, the agent conditions its generation on these accumulated skills, producing changes grounded in the project's own evolution rather than generic pretraining priors. Evaluation is conducted on genuinely future, merged pull requests that could not have been seen during the skill-building phase, and spans multiple dimensions including functional correctness, code-style consistency, internal API reuse rate, and modified-region plausibility. Experiments on an expert-maintained repository with rich commit history show that Online Repository Memory effectively improves organicity scores on held-out future tasks.

Large Language Models (LLMs) have made significant strides in mathematical reasoning, underscoring the need for a comprehensive and fair evaluation of their capabilities. However, existing benchmarks often fall short, either lacking extensive coverage of undergraduate-level mathematical problems or probably suffering from test-set contamination. To address these issues, we introduce UGMathBench, a diverse and dynamic benchmark specifically designed for evaluating undergraduate-level mathematical reasoning with LLMs. UGMathBench comprises 5,062 problems across 16 subjects and 111 topics, featuring 10 distinct answer types. Each problem includes three randomized versions, with additional versions planned for release as leading open-source LLMs become saturated in UGMathBench. Furthermore, we propose two key metrics: effective accuracy (EAcc), which measures the percentage of correctly solved problems across all three versions, and reasoning gap (Delta), which assesses reasoning robustness by calculating the difference between the average accuracy across all versions and EAcc. Our extensive evaluation of 23 leading LLMs reveals that the highest EAcc achieved is 56.3\% by OpenAI-o1-mini, with large Delta values observed across different models. This highlights the need for future research aimed at developing "large reasoning models" with high EAcc and Delta = 0. We anticipate that the release of UGMathBench, along with its detailed evaluation codes, will serve as a valuable resource to advance the development of LLMs in solving mathematical problems.

Bug-fix benchmarks are essential for evaluating methodologies in automatic program repair (APR) and fault localization (FL). However, existing benchmarks, exemplified by Defects4J, need to evolve to incorporate recent bug-fixes aligned with contemporary development practices. Moreover, reproducibility, a key scientific principle, has been lacking in bug-fix benchmarks. To address these gaps, we present GitBug-Java, a reproducible benchmark of recent Java bugs. GitBug-Java features 199 bugs extracted from the 2023 commit history of 55 notable open-source repositories. The methodology for building GitBug-Java ensures the preservation of bug-fixes in fully-reproducible environments. We publish GitBug-Java at https://github.com/gitbugactions/gitbug-java.

Time-dependent data-generating distributions have proven to be difficult for gradient-based training of neural networks, as the greedy updates result in catastrophic forgetting of previously learned knowledge. Despite the progress in the field of continual learning to overcome this forgetting, we show that a set of common state-of-the-art methods still suffers from substantial forgetting upon starting to learn new tasks, except that this forgetting is temporary and followed by a phase of performance recovery. We refer to this intriguing but potentially problematic phenomenon as the stability gap. The stability gap had likely remained under the radar due to standard practice in the field of evaluating continual learning models only after each task. Instead, we establish a framework for continual evaluation that uses per-iteration evaluation and we define a new set of metrics to quantify worst-case performance. Empirically we show that experience replay, constraint-based replay, knowledge-distillation, and parameter regularization methods are all prone to the stability gap; and that the stability gap can be observed in class-, task-, and domain-incremental learning benchmarks. Additionally, a controlled experiment shows that the stability gap increases when tasks are more dissimilar. Finally, by disentangling gradients into plasticity and stability components, we propose a conceptual explanation for the stability gap.

Large language models (LLMs) have demonstrated remarkable proficiency in generating detailed and coherent explanations of complex concepts. However, the extent to which these models truly comprehend the concepts they articulate remains unclear. To assess the level of comprehension of a model relative to the content it generates, we implemented a self-evaluation pipeline where models: (i) given a topic generate an excerpt with information about the topic, (ii) given an excerpt generate question-answer pairs, and finally (iii) given a question generate an answer. We refer to this self-evaluation approach as Explain-Query-Test (EQT). Interestingly, the accuracy on generated questions resulting from running the EQT pipeline correlates strongly with the model performance as verified by typical benchmarks such as MMLU-Pro. In other words, EQT's performance is predictive of MMLU-Pro's, and EQT can be used to rank models without the need for any external source of evaluation data other than lists of topics of interest. Moreover, our results reveal a disparity between the models' ability to produce detailed explanations and their performance on questions related to those explanations. This gap highlights fundamental limitations in the internal knowledge representation and reasoning abilities of current LLMs. We release the code at https://github.com/asgsaeid/EQT.

We describe a verification pipeline that takes production Rust cryptographic code and produces machine-checked correctness proofs in Lean 4. The pipeline combines three components: symbolic extraction tools (Charon and Aeneas, or Hax) that lift Rust into Lean 4; formal cryptographic specification libraries (ArkLib and CompPoly, from the Verified zkEVM project) that provide the mathematical targets; and AI provers (Aristotle from Harmonic AI and Aleph from Logical Intelligence) that close the resulting proof obligations. Every proof is checked by the Lean kernel, so AI output cannot compromise soundness. Within the scope of the Ethereum Foundation's zkEVM Verification Project, we applied the pipeline to cryptographic primitives in Plonky3 (FRI folding, Mersenne31 and KoalaBear field arithmetic, Horner polynomial evaluation) and RISC Zero (Merkle inclusion verification). In addition, Aleph authored proofs of two bounds-style theorems in Plonky3's compute_log_arity_for_round that previously stood as sorry. The paper describes the architecture, walks through a running example based on Aleph's two proofs, reports which classes of proof obligations AI closed and which required manual work, and discusses the engineering gaps we encountered: Lean 4 toolchain drift across tools and specific Aeneas/Hax extraction limits. We also document concrete missing lemmas, tactic gaps, and code-generation friction points discovered during proof development. We hope this contribution lowers the barrier to adoption of formal verification and facilitates more effective use of AI in this pipeline. The result is a working pipeline for formal verification of Rust, with kernel-checked proofs and reproducible artefacts.

Code generation models can help improve many common software tasks ranging from code completion to defect prediction. Most of the existing benchmarks for code generation LLMs focus on code authoring or code completion. Surprisingly, there has been far less effort dedicated to benchmarking software testing, despite the strong correlation between well-tested software and effective bug detection. To address this gap, we create and release TestGenEval, a large-scale benchmark to measure test generation performance. Based on SWEBench, TestGenEval comprises 68,647 tests from 1,210 code and test file pairs across 11 well-maintained Python repositories. It covers initial tests authoring, test suite completion, and code coverage improvements. Test authoring simulates the process of a developer writing a test suite from scratch, while test completion mimics the scenario where a developer aims to improve the coverage of an existing test suite. We evaluate several popular models, with sizes ranging from 7B to 405B parameters. Our detailed analysis highlights TestGenEval's contribution to a comprehensive evaluation of test generation performance. In particular, models struggle to generate high-coverage test suites, with the best model, GPT-4o, achieving an average coverage of only 35.2%. This is primarily due to models struggling to reason about execution, and their frequent assertion errors when addressing complex code paths.

Existing benchmarks for frontier models often test specialized, ``PhD-level'' knowledge that is difficult for non-experts to grasp. In contrast, we present a benchmark based on the NPR Sunday Puzzle Challenge that requires only general knowledge. Our benchmark is challenging for both humans and models, however correct solutions are easy to verify, and models' mistakes are easy to spot. Our work reveals capability gaps that are not evident in existing benchmarks: OpenAI o1 significantly outperforms other reasoning models that are on par on benchmarks that test specialized knowledge. Furthermore, our analysis of reasoning outputs uncovers new kinds of failures. DeepSeek R1, for instance, often concedes with ``I give up'' before providing an answer that it knows is wrong. R1 can also be remarkably ``uncertain'' in its output and in rare cases, it does not ``finish thinking,'' which suggests the need for an inference-time technique to ``wrap up'' before the context window limit is reached. We also quantify the effectiveness of reasoning longer with R1 and Gemini Thinking to identify the point beyond which more reasoning is unlikely to improve accuracy on our benchmark.

Software requirement ambiguity is ubiquitous in real-world development, stemming from the inherent imprecision of natural language and the varying interpretations of stakeholders. While Large Language Models (LLMs) have demonstrated impressive capabilities in generating code from precise specifications, such ambiguity poses a significant obstacle to reliable automated code generation. Existing benchmarks typically assume clear and unambiguous requirements, leaving an empirical gap in understanding how LLMs behave when faced with the inherent uncertainty of real-world software requirements. In this paper, we introduce Orchid, the first code generation benchmark specifically designed with ambiguous requirements. It comprises 1,304 function-level tasks covering four distinct types of ambiguity: lexical, syntactic, semantic, and vagueness. Leveraging this dataset, we conduct the first systematic empirical study to evaluate the impact of requirement ambiguity on LLM-based code generation. Our results demonstrate that ambiguity consistently degrades the performance of all evaluated LLMs, with the most pronounced negative effects observed in highly advanced models. Furthermore, we observe that LLMs frequently produce functionally divergent implementations for the same ambiguous requirement and lack the capability to identify or resolve such ambiguity autonomously. These findings reveal a significant performance gap between clear and ambiguous requirements, underscoring the urgent need for ambiguity-aware techniques in the next generation of automated software engineering tools. The Orchid benchmark is publicly available at https://huggingface.co/datasets/SII-YDD/Orchid.

We pursue a vision for self-improving language models in which the model does not merely generate problems or traces to imitate, but constructs the environments that train it. In zero-data reasoning RL, this reframes self-improvement from a data-generation loop into an environment-construction loop, where each artifact is a reusable executable object that samples instances, computes references, and scores responses. Whether this vision sustains improvement hinges on a single property: the environments must exhibit stable solve--verify asymmetry, the model must be able to write an oracle once that it cannot reliably execute in natural language on fresh instances. This asymmetry takes two complementary forms. Some tasks are algorithmically hard to reason through but trivial as code: a dynamic program or graph traversal, compiled once, yields unboundedly many calibrated instances. Others are intrinsically hard to solve but easy to verify, like planted subset-sum or constraint satisfaction. Both create a durable gap between proposing and solving that the policy cannot close by gaming the verifier, and it is this gap that keeps reward informative as the learner improves. We instantiate this view in EvoEnv, a single-policy generator, solver method that synthesizes Python environments from ten seeds and admits them only after staged validation, semantic self-review, solver-relative difficulty calibration, and novelty checks. The strongest evidence comes from the already-strong regime: on Qwen3-4B-Thinking, fixed public-data RLVR and fixed hand-crafted environment RLVR reduce the average, while EvoEnv improves it from 72.4 to 74.8, a relative gain of 3.3%. Stable self-improvement, we suggest, depends not on producing more synthetic data, but on models learning to construct worlds whose difficulty stays structurally beyond their own reach.

Program synthesis has been long studied with recent approaches focused on directly using the power of Large Language Models (LLMs) to generate code. Programming benchmarks, with curated synthesis problems and test-cases, are used to measure the performance of various LLMs on code synthesis. However, these test-cases can be limited in both quantity and quality for fully assessing the functional correctness of the generated code. Such limitation in the existing benchmarks begs the following question: In the era of LLMs, is the code generated really correct? To answer this, we propose EvalPlus -- a code synthesis evaluation framework to rigorously benchmark the functional correctness of LLM-synthesized code. EvalPlus augments a given evaluation dataset with large amounts of test-cases newly produced by an automatic test input generator, powered by both LLM- and mutation-based strategies. While EvalPlus is general, we extend the test-cases of the popular HumanEval benchmark by 80x to build HumanEval+. Our extensive evaluation across 26 popular LLMs (e.g., GPT-4 and ChatGPT) demonstrates that HumanEval+ is able to catch significant amounts of previously undetected wrong code synthesized by LLMs, reducing the pass@k by up-to 19.3-28.9%. We also surprisingly found that test insufficiency can lead to mis-ranking. For example, both WizardCoder-CodeLlama and Phind-CodeLlama now outperform ChatGPT on HumanEval+, while none of them could on HumanEval. Our work not only indicates that prior popular code synthesis evaluation results do not accurately reflect the true performance of LLMs for code synthesis, but also opens up a new direction to improve such programming benchmarks through automated testing. We have open-sourced our tools, enhanced datasets as well as all LLM-generated code at https://github.com/evalplus/evalplus to facilitate and accelerate future LLM-for-code research.

Discovering causal regularities and applying them to build functional systems--the discovery-to-application loop--is a hallmark of general intelligence, yet evaluating this capacity has been hindered by the vast complexity gap between scientific discovery and real-world engineering. We introduce SciCrafter, a Minecraft-based benchmark that operationalizes this loop through parameterized redstone circuit tasks. Agents must ignite lamps in specified patterns (e.g., simultaneously or in timed sequences); scaling target parameters substantially increases construction complexity and required knowledge, forcing genuine discovery rather than reliance on memorized solutions. Evaluating frontier models including GPT-5.2, Gemini-3-Pro, and Claude-Opus-4.5 under a general-purpose code agent scaffold, we find that all plateau at approximately 26% success rate. To diagnose these failures, we decompose the loop into four capacities--knowledge gap identification, experimental discovery, knowledge consolidation, and knowledge application--and design targeted interventions whose marginal contributions serve as proxies for corresponding gaps. Our analysis reveals that although the general knowledge application capability still remains as the biggest gap across all models, for frontier models the knowledge gap identification starts to become a major hurdle--indicating the bottleneck is shifting from solving problems right to raising the right problems for current AI. We release SciCrafter as a diagnostic probe for future research on AI systems that navigate the full discovery-to-application loop.

Effective scheduling under tight resource, timing, and operational constraints underpins large-scale planning across sectors such as capital projects, manufacturing, logistics, and IT fleet transitions. However, the reliability of large language models (LLMs) when reasoning under high-constraint regimes is insufficiently characterized. To address this gap, we present R-ConstraintBench, a scalable framework that evaluates models on Resource-Constrained Project Scheduling Problems (RCPSP), an NP-Complete feasibility class, while difficulty increases via linear growth in constraints. R-ConstraintBench incrementally increases non-redundant precedence constraints in Directed Acyclic Graphs (DAGs) and then introduces downtime, temporal windows, and disjunctive constraints. As an illustrative example, we instantiate the benchmark in a data center migration setting and evaluate multiple LLMs using feasibility and error analysis, identifying degradation thresholds and constraint types most associated with failure. Empirically, strong models are near-ceiling on precedence-only DAGs, but feasibility performance collapses when downtime, temporal windows, and disjunctive constraints interact, implicating constraint interaction, not graph depth, as the principal bottleneck. Performance on clean synthetic ramps also does not guarantee transfer to domain-grounded scenarios, underscoring limited generalization.

Mathematical reasoning remains a significant challenge for Large Language Models (LLMs) due to hallucinations. When combined with formal proof assistants like Lean, these hallucinations can be eliminated through rigorous verification, making theorem proving reliable. However, even with formal verification, LLMs still struggle with long proofs and complex mathematical formalizations. While Lean with LLMs offers valuable assistance with retrieving lemmas, generating tactics, or even complete proofs, it lacks a crucial capability: providing a sense of proof progress. This limitation particularly impacts the overall development efficiency in large formalization projects. We introduce LeanProgress, a method that predicts the progress in the proof. Training and evaluating our models made on a large corpus of Lean proofs from Lean Workbook Plus and Mathlib4 and how many steps remain to complete it, we employ data preprocessing and balancing techniques to handle the skewed distribution of proof lengths. Our experiments show that LeanProgress achieves an overall prediction accuracy of 75.1\% in predicting the amount of progress and, hence, the remaining number of steps. When integrated into a best-first search framework using Reprover, our method shows a 3.8\% improvement on Mathlib4 compared to baseline performances of 41.2\%, particularly for longer proofs. These results demonstrate how proof progress prediction can enhance both automated and interactive theorem proving, enabling users to make more informed decisions about proof strategies.

Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To address this gap, we introduce EffiBench-X, the first multi-language benchmark designed to measure the efficiency of LLM-generated code. EffiBench-X supports Python, C++, Java, JavaScript, Ruby, and Golang. It comprises competitive programming tasks with human-expert solutions as efficiency baselines. Evaluating state-of-the-art LLMs on EffiBench-X reveals that while models generate functionally correct code, they consistently underperform human experts in efficiency. Even the most efficient LLM-generated solutions (Qwen3-32B) achieve only around 62\% of human efficiency on average, with significant language-specific variations. LLMs show better efficiency in Python, Ruby, and JavaScript than in Java, C++, and Golang. For instance, DeepSeek-R1's Python code is significantly more efficient than its Java code. These results highlight the critical need for research into LLM optimization techniques to improve code efficiency across diverse languages. The dataset and evaluation infrastructure are submitted and available at https://github.com/EffiBench/EffiBench-X.git and https://huggingface.co/datasets/EffiBench/effibench-x.

Code generation has largely improved development efficiency in the era of large language models (LLMs). With the ability to follow instructions, current LLMs can be prompted to generate code solutions given detailed descriptions in natural language. Many research efforts are being devoted to improving the correctness of LLM-generated code, and many benchmarks are proposed to evaluate the correctness comprehensively. Despite the focus on correctness, the time efficiency of LLM-generated code solutions is under-explored. Current correctness benchmarks are not suitable for time efficiency evaluation since their test cases cannot well distinguish the time efficiency of different code solutions. Besides, the current execution time measurement is not stable and comprehensive, threatening the validity of the time efficiency evaluation. To address the challenges in the time efficiency evaluation of code generation, we propose COFFE, a code generation benchmark for evaluating the time efficiency of LLM-generated code solutions. COFFE contains 398 and 358 problems for function-level and file-level code generation, respectively. To improve the distinguishability, we design a novel stressful test case generation approach with contracts and two new formats of test cases to improve the accuracy of generation. For the time evaluation metric, we propose efficienct@k based on CPU instruction count to ensure a stable and solid comparison between different solutions. We evaluate 14 popular LLMs on COFFE and identify four findings. Based on the findings, we draw some implications for LLM researchers and software practitioners to facilitate future research and usage of LLMs in code generation.

AI systems increasingly produce fluent, correct, end-to-end outcomes. Over time, this erodes users' ability to explain, verify, or intervene. We define this divergence as the Capability-Comprehension Gap: a decoupling where assisted performance improves while users' internal models deteriorate. This paper argues that prevailing approaches to transparency, user control, literacy, and governance do not define the foundational understanding humans must retain for oversight under sustained AI delegation. To formalize this, we define the Cognitive Integrity Threshold (CIT) as the minimum comprehension required to preserve oversight, autonomy, and accountable participation under AI assistance. CIT does not require full reasoning reconstruction, nor does it constrain automation. It identifies the threshold beyond which oversight becomes procedural and contestability fails. We operatinalize CIT through three functional dimensions: (i) verification capacity, (ii) comprehension-preserving interaction, and (iii) institutional scaffolds for governance. This motivates a design and governance agenda that aligns human-AI interaction with cognitive sustainability in responsibility-critical settings.

The emergence of large language models (LLMs) has significantly pushed the frontiers of program synthesis. Advancement of LLM-based program synthesis calls for a thorough evaluation of LLM-generated code. Most evaluation frameworks focus on the (functional) correctness of generated code; efficiency, as an important measure of code quality, has been overlooked in existing evaluations. In this work, we develop ENAMEL (EfficeNcy AutoMatic EvaLuator), a rigorous and high-standard benchmark for evaluating the capability of LLMs in generating efficient code. Firstly, we propose a new efficiency metric called eff@k, which generalizes the pass@k metric from correctness to efficiency and appropriately handles right-censored execution time. Furthermore, we derive an unbiased and variance-reduced estimator of eff@k via Rao--Blackwellization; we also provide a numerically stable implementation for the new estimator. Secondly, to set a high-standard for efficiency evaluation, we employ a human expert to design best algorithms and implementations as our reference solutions of efficiency, many of which are much more efficient than existing canonical solutions in HumanEval and HumanEval+. Moreover, to ensure a rigorous evaluation, we employ a human expert to curate strong test case generators to filter out wrong code and differentiate suboptimal algorithms. An extensive study across 30 popular LLMs using our benchmark ENAMEL shows that LLMs still fall short of generating expert-level efficient code. Using two subsets of our problem set, we demonstrate that such deficiency is because current LLMs struggle in designing advanced algorithms and are barely aware of implementation optimization. Our benchmark is publicly available at https://github.com/q-rz/enamel .

Large language models are increasingly deployed as agents that solve tasks by interacting with external tool environments. Although recent tool-use benchmarks increasingly cover complex task settings, they still largely assume clean, stable, and trustworthy tool environments, leaving tool-environment unreliability insufficiently examined. We introduce ToolBench-X, a benchmark for evaluating agents under recoverable reliability hazards. ToolBench-X contains executable multi-step tasks across diverse domains and sequential, parallel, and mixed workflows, each paired with deterministic tools and a canonical final answer for automatic evaluation. Starting from clean tool environments, ToolBench-X injects five structured hazard types: Specification Drift, Invocation Error, Execution Failure, Output Drift, and Cross-source Conflict. Crucially, each injected instance remains solvable through at least one valid recovery path, such as retrying, fallback, verification, or cross-checking. Experiments reveal a substantial reliability gap: agents that perform well with reliable tools often fail under recoverable hazards. Further analysis shows that failures are driven less by tool-use volume or inference budget than by limited hazard diagnosis and ineffective recovery. Targeted recovery hints recover many failed tasks, while test-time scaling yields more limited gains. These results suggest that tool-use evaluation should move beyond function-call accuracy toward task completion under unreliable tool environments. The code and data is available at https://github.com/Foreverskyou/ToolBench-X.

Large language models (LLMs) are increasingly integrated in software development, but ensuring correctness in LLM-generated code remains challenging and often requires costly manual review. Verifiable code generation -- jointly generating code, specifications, and proofs of code-specification alignment -- offers a promising path to address this limitation and further unleash LLMs' benefits in coding. Yet, there exists a significant gap in evaluation: current benchmarks often lack support for end-to-end verifiable code generation. In this paper, we introduce Verina (Verifiable Code Generation Arena), a high-quality benchmark enabling a comprehensive and modular evaluation of code, specification, and proof generation as well as their compositions. Verina consists of 189 manually curated coding tasks in Lean, with detailed problem descriptions, reference implementations, formal specifications, and extensive test suites. Our extensive evaluation of state-of-the-art LLMs reveals significant challenges in verifiable code generation, especially in proof generation, underscoring the need for improving LLM-based theorem provers in verification domains. The best model, OpenAI o4-mini, generates only 61.4% correct code, 51.0% sound and complete specifications, and 3.6% successful proofs, with one trial per task. We hope Verina will catalyze progress in verifiable code generation by providing a rigorous and comprehensive benchmark. We release our dataset on https://huggingface.co/datasets/sunblaze-ucb/verina and our evaluation code on https://github.com/sunblaze-ucb/verina.

The fast-growing demands in using Large Language Models (LLMs) to tackle complex multi-step data science tasks create an emergent need for accurate benchmarking. There are two major gaps in existing benchmarks: (i) the lack of standardized, process-aware evaluation that captures instruction adherence and process fidelity, and (ii) the scarcity of accurately labeled training data. To bridge these gaps, we introduce DARE-bench, a benchmark designed for machine learning modeling and data science instruction following. Unlike many existing benchmarks that rely on human- or model-based judges, all tasks in DARE-bench have verifiable ground truth, ensuring objective and reproducible evaluation. To cover a broad range of tasks and support agentic tools, DARE-bench consists of 6,300 Kaggle-derived tasks and provides both large-scale training data and evaluation sets. Extensive evaluations show that even highly capable models such as gpt-o4-mini struggle to achieve good performance, especially in machine learning modeling tasks. Using DARE-bench training tasks for fine-tuning can substantially improve model performance. For example, supervised fine-tuning boosts Qwen3-32B's accuracy by 1.83x and reinforcement learning boosts Qwen3-4B's accuracy by more than 8x. These significant improvements verify the importance of DARE-bench both as an accurate evaluation benchmark and critical training data.

Interactive LLM agents are becoming part of daily work, but they do not reliably become easier to work with over time: a correction remembered in one session may still be violated in the next. We study this gap between preference access and preference compliance. In tasks derived from anonymized real-user friction cases, Mem0 memory still leaves 57.5% of applicable preference checks violated. We introduce Test-time Rule Acquisition and Compiled Enforcement (TRACE), a drop-in skill-layer pipeline for coding-agent runtimes that mines user corrections, rewrites them as atomic rules, and compiles them into runtime checks that must pass before an agent completes future tasks. Unlike runtime checks written ahead of time by developers, TRACE skills come from the user's own chat corrections. We evaluate TRACE with simulated user-in-the-loop experiments on ClawArena coding-agent tasks and MemoryArena-derived memory-intensive tasks. On ClawArena, TRACE reduces held-out preference violation from 100.0% to 37.6% on in-distribution tasks and from 100.0% to 2.0% on out-of-distribution tasks. On MemoryArena-derived tasks, TRACE reduces in-distribution violation from 100.0% to 60.5% while matching or exceeding the strongest memory baseline on task pass. These results suggest that compiling corrections into runtime enforcement can address a repeated-friction failure mode that memory alone does not reliably solve, reducing the need for users to restate the same correction across future sessions. Experiment code is available at https://github.com/YujunZhou/TRACE_exp, and the deployable skill is available at https://github.com/YujunZhou/tellonce.

Unified Multimodal Models (UMMs) exhibit strong understanding, yet this capability often fails to effectively guide generation. We identify this as a Cognitive Gap: the model lacks the understanding of how to enhance its own generation process. To bridge this gap, we propose Endogenous Reprompting, a mechanism that transforms the model's understanding from a passive encoding process into an explicit generative reasoning step by generating self-aligned descriptors during generation. To achieve this, we introduce SEER (Self-Evolving Evaluator and Reprompter), a training framework that establishes a two-stage endogenous loop using only 300 samples from a compact proxy task, Visual Instruction Elaboration. First, Reinforcement Learning with Verifiable Rewards (RLVR) activates the model's latent evaluation ability via curriculum learning, producing a high-fidelity endogenous reward signal. Second, Reinforcement Learning with Model-rewarded Thinking (RLMT) leverages this signal to optimize the generative reasoning policy. Experiments show that SEER consistently outperforms state-of-the-art baselines in evaluation accuracy, reprompting efficiency, and generation quality, without sacrificing general multimodal capabilities.

Recent reports claim that large language models (LLMs) now outperform elite humans in competitive programming. Drawing on knowledge from a group of medalists in international algorithmic contests, we revisit this claim, examining how LLMs differ from human experts and where limitations still remain. We introduce LiveCodeBench Pro, a benchmark composed of problems from Codeforces, ICPC, and IOI that are continuously updated to reduce the likelihood of data contamination. A team of Olympiad medalists annotates every problem for algorithmic categories and conducts a line-by-line analysis of failed model-generated submissions. Using this new data and benchmark, we find that frontier models still have significant limitations: without external tools, the best model achieves only 53% pass@1 on medium-difficulty problems and 0% on hard problems, domains where expert humans still excel. We also find that LLMs succeed at implementation-heavy problems but struggle with nuanced algorithmic reasoning and complex case analysis, often generating confidently incorrect justifications. High performance appears largely driven by implementation precision and tool augmentation, not superior reasoning. LiveCodeBench Pro thus highlights the significant gap to human grandmaster levels, while offering fine-grained diagnostics to steer future improvements in code-centric LLM reasoning.

We introduce Differential Performance Evaluation (DPE), a framework designed to reliably evaluate Large Language Models (LLMs) for efficient code generation. Traditional coding benchmarks often fail to provide reliable insights into code efficiency, due to their reliance on simplistic test inputs and the absence of effective compound metrics. DPE addresses these issues by focusing on efficiency-demanding programming tasks and establishing an insightful compound metric for performance evaluation. DPE operates in two phases: To curate efficiency datasets, it selects efficiency-demanding tasks from existing coding benchmarks and generates computationally expensive inputs to stress the efficiency of LLM solutions. To assess the code efficiency, DPE profiles the new solution and compares it globally against a set of reference solutions that exhibit distinct efficiency levels, where the matched level defines its efficiency score. As a proof of concept, we use DPE to create EvalPerf, a benchmark with 121 performance-challenging coding tasks. Our comprehensive evaluation draws interesting findings on the efficiency impact of model sizes, instruction tuning, and prompting. For example, while the scaling law fails to account for code efficiency, general instruction tuning benefits both code correctness and efficiency. We also evaluate the evaluation by examining the effectiveness of DPE, showing that EvalPerf is reliable and convenient to use even across platforms.

We study the accuracy of differentially private mechanisms in the continual release model. A continual release mechanism receives a sensitive dataset as a stream of T inputs and produces, after receiving each input, an accurate output on the obtained inputs. In contrast, a batch algorithm receives the data as one batch and produces a single output. We provide the first strong lower bounds on the error of continual release mechanisms. In particular, for two fundamental problems that are widely studied and used in the batch model, we show that the worst case error of every continual release algorithm is tilde Omega(T^{1/3}) times larger than that of the best batch algorithm. Previous work shows only a polylogarithimic (in T) gap between the worst case error achievable in these two models; further, for many problems, including the summation of binary attributes, the polylogarithmic gap is tight (Dwork et al., 2010; Chan et al., 2010). Our results show that problems closely related to summation -- specifically, those that require selecting the largest of a set of sums -- are fundamentally harder in the continual release model than in the batch model. Our lower bounds assume only that privacy holds for streams fixed in advance (the "nonadaptive" setting). However, we provide matching upper bounds that hold in a model where privacy is required even for adaptively selected streams. This model may be of independent interest.

Existing computer-use agents remain fundamentally limited in professional software manipulation: GUI-based agents suffer from fragile visual grounding and long-horizon error accumulation, while API-basedapproaches struggle with heterogeneous protocols and inaccessible commercial interfaces. In this work,we identify the Component Object Model (COM) as a unified executable abstraction, proposing COM-as-Action: a new paradigm that reframes professional software interaction as deterministic program synthesisrather than sequential visual control. To validate this paradigm in the most demanding environments, weintroduce ComCADBench, the first benchmark for agents operating real industrial CAD software. Ourexperiments reveal a substantial paradigm gap: frontier proprietary models achieve near-zero successunder GUI-based interaction, whereas COM-based execution yields substantial immediate gains. Tobridge the remaining gap between syntactic correctness and geometric accuracy, we develop ComActor, aself-correcting agent trained through a progressive three-stage framework, alongside ComForge, a scalableplatform for large-scale training in Windows containers. Extensive experiments show that ComActorachieves state-of-the-art performance on ComCADBench, with strong resilience in long-horizon taskswhere baselines collapse, and generalizes to external CAD benchmark.

When writing programs, people have the ability to tackle a new complex task by decomposing it into smaller and more familiar subtasks. While it is difficult to measure whether neural program synthesis methods have similar capabilities, we can measure whether they compositionally generalize, that is, whether a model that has been trained on the simpler subtasks is subsequently able to solve more complex tasks. In this paper, we characterize several different forms of compositional generalization that are desirable in program synthesis, forming a meta-benchmark which we use to create generalization tasks for two popular datasets, RobustFill and DeepCoder. We then propose ExeDec, a novel decomposition-based synthesis strategy that predicts execution subgoals to solve problems step-by-step informed by program execution at each step. ExeDec has better synthesis performance and greatly improved compositional generalization ability compared to baselines.

Large language models (LLMs) can translate natural language into optimization code, but silent failures pose a critical risk: code that executes and returns solver-feasible solutions may encode semantically incorrect formulations, creating a feasibility-correctness gap of up to 90 percentage points on compositional problems. We introduce ReLoop, addressing silent failures from two complementary directions. Structured generation decomposes code production into a four-stage reasoning chain (understand, formalize, synthesize, verify) that mirrors expert modeling practice, with explicit variable-type reasoning and self-verification to prevent formulation errors at their source. Behavioral verification detects errors that survive generation by testing whether the formulation responds correctly to solver-based parameter perturbation, without requiring ground truth -- an external semantic signal that bypasses the self-consistency problem inherent in LLM-based code review. The two mechanisms are complementary: structured generation dominates on complex compositional problems, while behavioral verification becomes the largest single contributor on problems with localized formulation defects. Together with execution recovery via IIS-enhanced diagnostics, ReLoop raises correctness from 22.6% to 31.1% and execution from 72.1% to 100.0% on the strongest model, with consistent gains across five models spanning three paradigms (foundation, SFT, RL) and three benchmarks. We additionally release RetailOpt-190, 190 compositional retail optimization scenarios targeting the multi-constraint interactions where LLMs most frequently fail.

The deployment of coding agents in privacy-sensitive and resource-constrained environments drives the demand for capable open-weight Small Language Models (SLMs). However, they suffer from a fundamental capability gap: unlike frontier large models, they lack the inference-time strong generalization to work with complicated, unfamiliar codebases. We identify that the prevailing Task-Centric Learning (TCL) paradigm, which scales exposure across disparate repositories, fails to address this limitation. In response, we propose Repository-Centric Learning (RCL), a paradigm shift that prioritizes vertical repository depth over horizontal task breadth, suggesting SLMs must internalize the "physics" of a target software environment through parametric knowledge acquisition, rather than attempting to recover it via costly inference-time search. Following this new paradigm, we design a four-unit Repository-Centric Experience, transforming static codebases into interactive learning signals, to train SWE-Spot-4B, a family of highly compact models built as repo-specialized experts that breaks established scaling trends, outperforming open-weight models up to larger (e.g., CWM by Meta, Qwen3-Coder-30B) and surpassing/matching efficiency-focused commercial models (e.g., GPT-4.1-mini, GPT-5-nano) across multiple SWE tasks. Further analysis reveals that RCL yields higher training sample efficiency and lower inference costs, emphasizing that for building efficient intelligence, repository mastery is a distinct and necessary dimension that complements general coding capability.

As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and stopped. This paper studies RL for LLM-based multi-agent systems through orchestration traces: temporal interaction graphs whose events include sub-agent spawning, delegation, communication, tool use, return, aggregation, and stopping decisions. Using this lens, we identify three technical axes. First, reward design spans eight families, including orchestration rewards for parallelism speedup, split correctness, and aggregation quality. Second, reward and credit signals attach to eight credit- or signal-bearing units from token to team; explicit counterfactual message-level credit remains especially sparse in our curated pool. Third, orchestration learning decomposes into five sub-decisions: when to spawn, whom to delegate to, how to communicate, how to aggregate, and when to stop. In our curated pool as of May 4, 2026, we found no explicit RL training method for the stopping decision. We connect academic methods to public industrial evidence from Kimi Agent Swarm, OpenAI Codex, and Anthropic Claude Code. The resulting scale gap is a gap between publicly reported deployment envelopes and open academic evaluation regimes, not independent verification of industrial training traces. We release the artifact at https://github.com/xxzcc/awesome-llm-mas-rl, including an 84-entry tagged paper pool, a 32-record exclusion log, scripted corpus statistics, and a minimal JSON schema for replayable orchestration traces.

High-quality chain-of-thought has demonstrated strong potential for unlocking the reasoning capabilities of large language models. However, current paradigms typically treat the reasoning process as an indivisible sequence, lacking an intrinsic mechanism to quantify step-wise information gain. This granularity gap manifests in two limitations: inference inefficiency from redundant exploration without explicit guidance, and optimization difficulty due to sparse outcome supervision or costly external verifiers. In this work, we propose CoT-Flow, a framework that reconceptualizes discrete reasoning steps as a continuous probabilistic flow, quantifying the contribution of each step toward the ground-truth answer. Built on this formulation, CoT-Flow enables two complementary methodologies: flow-guided decoding, which employs a greedy flow-based decoding strategy to extract information-efficient reasoning paths, and flow-based reinforcement learning, which constructs a verifier-free dense reward function. Experiments on challenging benchmarks demonstrate that CoT-Flow achieves a superior balance between inference efficiency and reasoning performance.

The rapid evolution of software libraries poses a considerable hurdle for code generation, necessitating continuous adaptation to frequent version updates while preserving backward compatibility. While existing code evolution benchmarks provide valuable insights, they typically lack execution-based evaluation for generating code compliant with specific library versions. To address this, we introduce GitChameleon, a novel, meticulously curated dataset comprising 328 Python code completion problems, each conditioned on specific library versions and accompanied by executable unit tests. GitChameleon rigorously evaluates the capacity of contemporary large language models (LLMs), LLM-powered agents, code assistants, and RAG systems to perform version-conditioned code generation that demonstrates functional accuracy through execution. Our extensive evaluations indicate that state-of-the-art systems encounter significant challenges with this task; enterprise models achieving baseline success rates in the 48-51\% range, underscoring the intricacy of the problem. By offering an execution-based benchmark emphasizing the dynamic nature of code libraries, GitChameleon enables a clearer understanding of this challenge and helps guide the development of more adaptable and dependable AI code generation methods. We make the dataset and evaluation code publicly available at https://github.com/mrcabbage972/GitChameleonBenchmark.

Vision language models are serving as general-purpose interfaces for complex multimodal tasks. However, deployment still faces three gaps: VLMs typically incur high latency and cost when processing dense video frames and long prompts, the agent scaffold remains static after deployment, and standard video-QA benchmarks do not test whether agents can use visual evidence inside tool-using workspaces. We present VisualClaw, a self-evolving multimodal agent built around two principles. First, hybrid encoding reduces deployment cost by filtering less informative streaming frames with a cascaded gate and compressing the text skill bank through hot/cold top-k injection. Second, skill evolution lets the agent learn from failures: retrieved memories condition an evolver as direct concatenated context or as guided evidence, producing skill-bank updates that help future questions. Across 4 video-QA benchmarks with 2 VLMs, VisualClaw cuts per-question API cost by an average -98% versus full-frame upload and by -25.9% over the offline uniform 8 frame baseline, while boosting accuracy in most settings, e.g., an average +3.85% and a peak +15.80% on EgoSchema with Gemini 3 Flash. To address the gap, we curate VisualClawArena, a 200-scenario multimodal agentic benchmark built through a strict five-stage pipeline; models must use video evidence, documents, dynamic updates, and executable checks inside a workspace. On VisualClawArena, the same framework with computer-use agent backends improves macro accuracy by +2.9% for Codex (GPT-5.5) and +3.2% for Claude Code (Sonnet 4.6) over no-evolution baselines, with a -9.5% cost reduction compared to the uniform-sampled baseline. These properties make VisualClaw a natural fit for edge applications, where the cascade reduces a 1-hour streaming session from ~3,600 API uploads down to only 5-20 calls and the self-evolution makes it a perfect personalized assistant.

Capability evaluation of large language models (LLMs) is increasingly shadowed by rising concerns of data contamination that cast doubts on whether static benchmarks measure genuine reasoning or mere memorization. We present an empirical study using an infinitely scalable framework to synthesize research-level QA directly from arXiv papers, harnessing the natural temporal structure of research publications where performance decay after knowledge cutoffs may indicate potential contamination. We evaluated 4 frontier model represented by 2 models of different knowledge cutoff dates per family on 1,643 multi-step reasoning questions synthesized from 20,277 arXiv papers stratified over 26 months, covering at least 6 months before and after all cutoff dates. Our results consistently showed a lack of significant performance decay near knowledge cutoff dates for models of various sizes, developers, and release dates. We further performed a comparative analysis with previous longitudinal studies that reported significant post-cutoff performance decay using directly retrieved questions based on public data. we hypothesize that the multi-step reasoning required by our synthesis pipeline offered additional complexity that goes deeper than shallow memorization, which effectively serves a mitigation strategy against benchmark contamination. We fully open source our code and dataset to aid reproducibility and advocate for a paradigm shift that prioritize reasoning-driven synthesis to construct benchmarks over simply collecting newly released questions periodically.

Code Executing Reasoning is becoming a new non-functional metric that assesses the ability of large language models (LLMs) in programming tasks. State-of-the-art frameworks (CodeMind or REval) and benchmarks (CruxEval) usually focus on LLM's prediction of a given code's input/output or intermediate variable states/values on limited programs. However, there is no tool for more in-depth analysis of the results. Without such a tool, the observations about LLM's code execution reasoning cannot be generalized to more datasets, preventing the research community and practitioners from devising the next generation of LLMs with better code execution reasoning abilities. This paper introduces ExeRScope, a series of tools and heuristics to analyze the result of code execution reasoning frameworks to understand better the impact of code properties in the studied benchmarks on the code execution reasoning. With such tooling, analysis can be generalized to code with similar properties without the urgent need to design more benchmarks, which is a cumbersome effort.

The training data for many Large Language Models (LLMs) is contaminated with test data. This means that public benchmarks used to assess LLMs are compromised, suggesting a performance gap between benchmark scores and actual capabilities. Ideally, a private holdout set could be used to accurately verify scores. Unfortunately, such datasets do not exist for most benchmarks, and post-hoc construction of sufficiently similar datasets is non-trivial. To address these issues, we introduce a systematic methodology for (i) retrospectively constructing a holdout dataset for a target dataset, (ii) demonstrating the statistical indistinguishability of this retro-holdout dataset, and (iii) comparing LLMs on the two datasets to quantify the performance gap due to the dataset's public availability. Applying these methods to TruthfulQA, we construct and release Retro-Misconceptions, on which we evaluate twenty LLMs and find that some have inflated scores by as much as 16 percentage points. Our results demonstrate that public benchmark scores do not always accurately assess model properties, and underscore the importance of improved data practices in the field.

As AI agents integrate into enterprise applications, their evaluation demands benchmarks that reflect the complexity of real-world operations. Instead, existing benchmarks overemphasize open-domains such as code, use narrow accuracy metrics, and lack authentic complexity. We present UNDERWRITE, an expert-first, multi-turn insurance underwriting benchmark designed in close collaboration with domain experts to capture real-world enterprise challenges. UNDERWRITE introduces critical realism factors often absent in current benchmarks: proprietary business knowledge, noisy tool interfaces, and imperfect simulated users requiring careful information gathering. Evaluating 13 frontier models, we uncover significant gaps between research lab performance and enterprise readiness: the most accurate models are not the most efficient, models hallucinate domain knowledge despite tool access, and pass^k results show a 20% drop in performance. The results from UNDERWRITE demonstrate that expert involvement in benchmark design is essential for realistic agent evaluation, common agentic frameworks exhibit brittleness that skews performance reporting, and hallucination detection in specialized domains demands compositional approaches. Our work provides insights for developing benchmarks that better align with enterprise deployment requirements.

Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative decoding (SD) accelerates autoregressive generation in serving systems, but its behavior under RL training remains largely unexplored. We identify three critical gaps that hinder the naive integration of SD into RL systems: diminishing speedups at large batch sizes, drafter staleness under continual actor updates, and drafter-induced policy degradation. To address these gaps, we present ReSpec, a system that adapts SD to RL through three complementary mechanisms: dynamically tuning SD configurations, evolving the drafter via knowledge distillation, and weighting updates by rollout rewards. On Qwen models (3B--14B), ReSpec achieves up to 4.5x speedup while preserving reward convergence and training stability, providing a practical solution for efficient RL-based LLM adaptation.

Code generation benchmarks such as HumanEval are widely adopted to evaluate LLMs' capabilities. However, after consolidating the latest 24 benchmarks, we noticed three significant imbalances. First, imbalanced programming language. 95.8% of benchmarks involve Python, while only 5 benchmarks involve Java. Second, imbalanced code granularity. Function-/statement-level benchmarks account for over 83.3% of benchmarks. Only a mere handful extends to class-/project-levels, and all are limited to Python. Third, lacking advanced features. Existing benchmarks primarily assess basic coding skills, while overlooking advanced Object-Oriented Programming (OOP) features (i.e., encapsulation, inheritance, and polymorphism). To fill these gaps, we propose JavaBench, a project-level Java benchmark that exercises OOP features. It comprises four Java projects with 389 methods in 106 Java classes. The test coverage is up to 92%, and JavaBench is attested by 282 undergraduate students, reaching a 90.93/100 average score (i.e., pass rate against the test suite), ensuring the quality of documentation, code skeleton, and tests. To better evaluate LLM's capability against JavaBench, we introduce a systematic evaluation design covering three context settings and five synthesis strategies at two granularities using three hierarchical metrics. Our extensive experiment yields several interesting findings. First, we noticed that regarding project-level Java programming, LLMs are far behind undergraduate students (no project can be correctly completed by any studied LLMs, and at most 41.17% Pass@5 in a more relaxed evaluation). Second, using method signature as prompt context may strike an ideal balance for project-level code generation. JavaBench is publicly available at https://github.com/java-bench/JavaBench.

Transformer-based language models for automatic code completion have shown great promise so far, yet the evaluation of these models rarely uses real data. This study provides both quantitative and qualitative assessments of three public code language models when completing real-world code. We first developed an open-source IDE extension, Code4Me, for the online evaluation of the models. We collected real auto-completion usage data for over a year from more than 1200 users, resulting in over 600K valid completions. These models were then evaluated using six standard metrics across twelve programming languages. Next, we conducted a qualitative study of 1690 real-world completion requests to identify the reasons behind the poor model performance. A comparative analysis of the models' performance in online and offline settings was also performed, using benchmark synthetic datasets and two masking strategies. Our findings suggest that while developers utilize code completion across various languages, the best results are achieved for mainstream languages such as Python and Java. InCoder outperformed the other models across all programming languages, highlighting the significance of training data and objectives. Our study also revealed that offline evaluations do not accurately reflect real-world scenarios. Upon qualitative analysis of the model's predictions, we found that 66.3% of failures were due to the models' limitations, 24.4% occurred due to inappropriate model usage in a development context, and 9.3% were valid requests that developers overwrote. Given these findings, we propose several strategies to overcome the current limitations. These include refining training objectives, improving resilience to typographical errors, adopting hybrid approaches, and enhancing implementations and usability.

Large Language Models (LLMs) are gaining popularity among software engineers. A crucial aspect of developing effective code generation LLMs is to evaluate these models using a robust benchmark. Evaluation benchmarks with quality issues can provide a false sense of performance. In this work, we conduct the first-of-its-kind study of the quality of prompts within benchmarks used to compare the performance of different code generation models. To conduct this study, we analyzed 3,566 prompts from 9 code generation benchmarks to identify quality issues in them. We also investigated whether fixing the identified quality issues in the benchmarks' prompts affects a model's performance. We also studied memorization issues of the evaluation dataset, which can put into question a benchmark's trustworthiness. We found that code generation evaluation benchmarks mainly focused on Python and coding exercises and had very limited contextual dependencies to challenge the model. These datasets and the developers' prompts suffer from quality issues like spelling and grammatical errors, unclear sentences to express developers' intent, and not using proper documentation style. Fixing all these issues in the benchmarks can lead to a better performance for Python code generation, but not a significant improvement was observed for Java code generation. We also found evidence that GPT-3.5-Turbo and CodeGen-2.5 models may have data contamination issues.

Code large language models (Code LLMs) have made significant progress in code generation by translating natural language descriptions into functional code; however, real-world applications often demand stricter adherence to detailed requirements such as coding style, line count, and structural constraints, beyond mere correctness. To address this, the paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs in controlled code generation, ensuring outputs align more closely with human-defined guidelines. The authors further present IFEvalCode, a multilingual benchmark comprising 1.6K test samples across seven programming languages (Python, Java, JavaScript, TypeScript, Shell, C++, and C#), with each sample featuring both Chinese and English queries. Unlike existing benchmarks, IFEvalCode decouples evaluation into two metrics: correctness (Corr.) and instruction-following (Instr.), enabling a more nuanced assessment. Experiments on over 40 LLMs reveal that closed-source models outperform open-source ones in controllable code generation and highlight a significant gap between the models' ability to generate correct code versus code that precisely follows instructions.

Automatic prompt optimization (APO) has emerged as a powerful paradigm for improving LLM performance without manual prompt engineering. Reflective APO methods such as GEPA iteratively refine prompts by diagnosing failure cases, but the optimization process remains black-box and label-free, leading to uninterpretable trajectories and systematic failure. We identify and empirically demonstrate four limitations: on GSM8K with a defective seed, GEPA degrades accuracy from 23.81% to 13.50%. We propose VISTA, a multi-agent APO framework that decouples hypothesis generation from prompt rewriting, enabling semantically labeled hypotheses, parallel minibatch verification, and interpretable optimization trace. A two-layer explore-exploit mechanism combining random restart and epsilon-greedy sampling further escapes local optima. VISTA recovers accuracy to 87.57% on the same defective seed and consistently outperforms baselines across all conditions on GSM8K and AIME2025.

LLM-agent budget overruns are a documented production failure class: a single retry loop can spend thousands of dollars before an operator notices, and the in-process integrity properties that would prevent it (no aliasing, no double-spend, no use-after-delegation of a cost-bearing value) are enforced, if at all, by ad-hoc wrappers rather than by the type system. Our central contribution is empirical: a catalog of 63 confirmed production incidents from 21 orchestration frameworks (2023-2026), each backed by a quoted GitHub issue and, where reported, a dollar loss, organized into an eight-cluster failure taxonomy (inter-rater Cohen's kappa = 0.837, N = 113), plus 47 supplementary structural entries. As one mitigation evaluated against this taxonomy, we build token-budgets, an 1,180-line Rust crate (no unsafe) that operationalizes affine ownership so that cloning, double-spending, or using a budget after delegating it are compile errors rather than runtime hazards an operator must remember to avoid. The dollar cap is runtime arithmetic under an estimator assumption; the affine layer makes that arithmetic non-bypassable. On single-agent workloads a 4-line Python counter matches the crate at 0/30 overshoot, so the distinguishing value is non-bypassability under operator error in multi-agent delegation: the delegation-fanout race documented in 11 incidents is rejected by the borrow checker at compile time, while the same pattern under asyncio overshoots 30/30 and three disciplined alternatives overshoot 0/30. Across five runtimes, three providers, and a temperature-stratified live-API test (N = 160), the approach reports zero cap violations and zero false refusals, at operational parity with concurrent work. Static over-reservation is 4-6x (2.11x adaptive). Binary-level cap-soundness on the running binary is left open.

Higher Degree by Research (HDR) candidates increasingly depend on cloud-provisioned virtual machines and local GPU hardware for their computational experiments, yet a persistent and under-addressed gap exists between having compute resources and using them productively. Cloud and infrastructure teams can provision virtual machines, but the path from a raw VM to a reproducible, GPU-ready research environment remains a significant barrier for researchers who are domain experts, not systems engineers. We identify this gap as a missing adapter layer between cloud provisioning and interactive research work. We present a lightweight, open-source solution built on k3s and Coder that implements this adapter layer and is already in active use in our research workspace environment. Our CI/CD pipeline connects GitHub directly to the local cluster, deploying research projects in under five minutes. We define a concrete metrics framework for evaluating this layer -- covering deployment latency, environment reproducibility, onboarding friction, and resource utilisation -- and establish baselines against which improvements can be measured.

Current coding-agent benchmarks usually pro- vide the full task specification upfront. Real research coding often does not: the intended system is progressively disclosed through in- teraction, requiring the agent to track durable design commitments across a long session. We introduce a benchmark for this setting and study faithfulne Ss Loss U nder eM ergent s Pecification (SLUMP), defined as the reduc- tion in final implementation faithfulness un- der emergent specification relative to a single- shot specification control. The benchmark con- tains 20 recent ML papers (10 ICML 2025, 10 NeurIPS 2025), 371 atomic verifiable compo- nents, and interaction scripts of approximately 60 coding requests that progressively disclose the target design without revealing the paper itself. Final repositories are scored with a five-level component-faithfulness rubric and accompanied by an exposure audit to verify that scored components are recoverable from the visible interaction. Evaluated on Claude Code and Codex, the single-shot specification control achieves higher overall implementation fidelity on 16/20 and 14/20 papers, respectively. Structural integration degrades under emergent specification on both platforms, while seman- tic faithfulness loss is substantial on Claude Code and small on Codex. As a mitigation case study, we introduce ProjectGuard, an exter- nal project-state layer for specification tracking. On Claude Code, ProjectGuard recovers 90% of the faithfulness gap, increases fully faith- ful components from 118 to 181, and reduces severe failures from 72 to 49. These results identify specification tracking as a distinct eval- uation target for long-horizon coding agents.

KV cache compression promises increased throughput and efficiency with negligible loss in performance. While the gains in throughput are indisputable and recent literature has indeed shown minimal degradation on particular benchmarks, in general the consequences of compression in realistic scenarios such as multi-instruction prompting have been insufficiently studied. In this paper, we identify several pitfalls practitioners should be aware of when deploying KV cache compressed LLMs. Importantly, we show that certain instructions degrade much more rapidly with compression, effectively causing them to be completely ignored by the LLM. As a practical example of that, we highlight system prompt leakage as a case study, empirically showing the impact of compression on leakage and general instruction following. We show several factors that play a role in prompt leakage: compression method, instruction order, and KV eviction bias. We then propose simple changes to KV cache eviction policies that can reduce the impact of these factors and improve the overall performance in multi-instruction tasks.