AI Software Engineering

Deep Neural Networks (DNNs) are increasingly being deployed in security-critical and safety-sensitive applications, which makes rigorous testing essential to identify and mitigate model weaknesses. Existing DNN testing approaches explore either the input space or a learned latent space. While latent-space generation can better maintain plausibility than direct input-space mutation, current methods still face a trade-off among exploration controllability, failure diversity, and seed-relative semantic drift. To overcome these limitations, we propose Latte, a black-box testing framework that generates semantically proximate, diverse, and fault-revealing test cases by leveraging the latent space. Specifically, Latte encodes each input seed with a pre-trained VQ-VAE and performs a seed-centered, one-step latent mutation along directions defined by anchors sampled from alternative classes, followed by quantization and decoding back to the input space. This explores local neighborhoods around each seed within the learned latent manifold, resulting in a larger number and broader diversity of oracle-triggering prediction discrepancies under the same budget. We evaluated Latte on 5 datasets and 10 DNN models in single-model and multi-model testing scenarios. Across the evaluated datasets and models, Latte improves fault exposure and behavioral diversity under matched testing budgets. Under the single-model setting, it also maintains low seed-relative semantic drift with respect to the source seeds.

Agentic AI coding tools write code with increasing autonomy and in doing so decide when to import a library and when to implement functionality from scratch. These decisions, whether to build functionality from scratch or buy into an external library, hereafter build-versus-buy, carry direct consequences for software security, licensing compliance, performance, and long-term maintainability. Yet no controlled experimental study has examined what governs build-versus-buy decisions in agentic AI coding tools. Configuration mechanisms, i.e., the means by which developers tailor agentic AI coding tool behavior to a project or workflow, are one of the primary means by which practitioners can influence these decisions. However, it is unclear which configuration mechanisms influence build-versus-buy decisions most effectively. We present a pre-registered protocol to study how configuration mechanisms alter build-versus-buy behavior in two popular agentic AI coding tools: Claude Code and OpenAI Codex. We will execute controlled programming tasks drawn from a benchmark of staged projects, each constructed around identifiable build-versus-buy points, and will manipulate the configuration supplied to each tool, ranging from no configuration, through context files with soft preferences and explicit prohibitions, to Skills (instructions that can be autonomously discovered), MCP-enabled library discovery tools, and permission controls, measuring which libraries the tool selects, whether it discloses newly introduced libraries, and whether those disclosures are complete and accurate. Nine pre-registered hypotheses structure the protocol. The resulting benchmark dataset and analysis pipeline will be released as a reusable artifact for evaluating build-versus-buy behavior in agentic AI coding tools.

Large language models for code generation often need to use APIs that are absent from their pretraining data. This requires more than recalling a function name: models must coordinate signatures, module paths, input-output contracts, semantics, and executable usage patterns. Existing novel-API benchmarks are typically static, rely on coarse pass/fail metrics, or use synthetic APIs that may not reflect real library evolution. We introduce NovelAPIBench, a fully automated dynamic benchmark that, for any base model and target library, discovers novel APIs, extracts decomposed knowledge bundles, generates executable coding tasks, and assigns failed samples to six diagnostic categories. Across about 1.9K tasks, four base models, and five domains, we compare knowledge injected through retrieval with knowledge internalized through parametric adaptation. We find that knowledge components are not interchangeable: usage examples are the strongest standalone signal, while the best two-component setting pairs signatures with either mechanisms or examples depending on the domain and backbone. Adding more context, especially source code, can hurt by increasing import-path errors. Parametric adaptation also does not replace retrieval once external knowledge is removed; rather, fine-tuning mainly teaches models how to use provided bundles, and this ability transfers to held-out libraries. These results suggest that retrieval and tuning play complementary roles: retrieval supplies volatile API content, while tuning improves procedural integration.

While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment techniques, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), typically apply coarse-grained optimization at the sequence level. This approach often fails to address the localized nature of security flaws, where a single incorrect token choice can compromise an entire program. To bridge this gap, we introduce Tree-like Self-Play (TSP), a framework that reframes secure code generation as a fine-grained sequential decision process. Unlike standard methods that blindly maximize likelihood, TSP constructs a decision tree where the model explores branching trajectories--generating both secure "golden paths" and vulnerable variants. By treating code generation as a self-play game, the model learns to strictly discriminate against its own localized errors. This provides a dense, on-policy learning signal that forces self-correction precisely at the critical decision nodes where vulnerabilities typically emerge. Our experiments demonstrate that TSP fundamentally enhances model reliability. In Python security benchmarks, TSP boosts CodeLlama-7B's pass rate (SPR@1) to 75.8%, significantly outperforming SFT (57.0%) and unstructured self-play baselines. Crucially, TSP induces robust out-of-distribution generalization: the model not only reduces vulnerabilities in unseen categories (CWEs) by 24.5% but also successfully transfers security principles learned from C/C++ to diverse languages, including Python, Go, and JavaScript. This suggests that TSP does not merely memorize patches, but internalizes abstract, language-agnostic security logic.

Stronger code agents are commonly assumed to be superior teachers for post-training, yet this assumption remains poorly disentangled from task difficulty, harness design, and student capacity. We investigate this pedagogical link using Terminal-Lego, a scalable pipeline that transforms multi-domain real-world issues into environment-verified agentic tasks. Surprisingly, standalone performance does not dictate teaching efficacy: while Claude Opus 4.6 achieves higher scores on Terminal-Bench 2.0, students fine-tuned on trajectories from DeepSeek-V3.2, a lower-scoring agent, exhibit significantly stronger generalization. We attribute this "pedagogical paradox" to Environment-Grounded Supervision (EGS): trajectories that explicitly expose inspect-act-verify behaviors through harness-visible interactions allow students to internalize robust problem-solving routines rather than fragile action sequences. Scaling analysis reveals exceptional data efficiency: with only 15.3k Terminal-Lego trajectories, for example, Qwen3-32B achieves a 24.3% score on Terminal-Bench 2.0, rivaling previous SOTA performance established with over 30x the data volume. Our results suggest that the frontier of agent post-training lies beyond mere outcome-matching, shifting the focus toward "Harness Engineering", where the systematic design of environment-grounded interaction structures serves as the primary catalyst for reproducible and generalizable agentic intelligence.

Multi-agent AI systems show promise for automating software engineering tasks, yet existing approaches suffer from coordination overhead, quality control gaps, and limited human oversight. We introduce SPOQ (Specialist Orchestrated Queuing), a methodology combining three innovations: (1) wave-based topological dispatch that computes parallel execution waves from task dependency graphs; (2) dual validation gates applying quality metrics before execution (planning validation) and after (code validation) to reduce rework cycles; and (3) Human-as-an-Agent (HaaA) integration, where a human specialist participates in decomposition and can be consulted during execution. SPOQ uses a three-tier agent hierarchy (Opus workers, Sonnet reviewers, Haiku investigators) to optimize cost-quality tradeoffs. We evaluate SPOQ through four experiments. Experiment 1: wave dispatch approaches the critical-path lower bound (ratio 1.03--1.11, speedup up to 14.3x); on a 2-slot local backend it delivers a stable 1.4x speedup. Experiment 2: SPOQ improves planning coverage from 93.0 to 99.75, eliminates cyclic plans, and lifts parallelism from 31.0 to 75.25. Experiment 3: dual validation reduces defects from 0.34 to 0.20 per task and lifts test pass rate from 91.25% to 99.75%. Experiment 4: human review reduces residual defects from 0.47 to 0.03 per task. Results are replicated on a locally hosted open-weights model (Qwen3.6-35B-A3B), verifying gains are attributable to orchestration rather than any specific model. A longitudinal study across 17 repositories, 8,589 commits, 1,822 tasks, and 13,866 tests (99.87% pass rate) provides ecological validation.

Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes. We introduce EvoTrainer, an autonomous training framework that co-evolves LLM policies and training-side harnesses through empirical feedback: it diagnoses rollout-level evidence, revises diagnostics, backtests interventions, and accumulates reusable skills. Evaluated on mathematical reasoning, competitive-programming code generation, and repository-level software engineering, EvoTrainer matches or exceeds the human-engineered RL references under the same data, codebase, and evaluation protocol, with the largest gain on long-horizon agentic SWE. Trajectory analyses show that retained strategies diverge across domains, evolving diagnostics prevent invalid high-scoring branches from being promoted, and reusable skills shape later search. Autonomous LLM RL should move beyond recipe search toward joint evolution of policies and the training harnesses that interpret them.

Large Language Models (LLMs) have demonstrated impressive performance across various domains, including code generation and problem solving. However, their application in robotic control, particularly in low-level tasks that require precise manipulation, real-time feedback, and environment-dependent execution, remains limited. To address this challenge, we propose the Closed-Loop Modular Code Synthesizer framework. This framework leverages a pre-trained LLM without any task-specific fine-tuning to perform modular code planning and generation, and iteratively executes the generated code while inserting debugging probes to observe its behavior. This closed-loop structure facilitates systematic debugging and refinement, ultimately producing executable control programs. We apply the proposed framework to the calibration of an RGB-D camera and a robotic arm, validating its effectiveness in real-world settings. Furthermore, through a subsequent pick-and-place task, we demonstrate not only the accuracy of the calibration but also the potential extensibility of the framework. Across both tasks, the framework achieved high execution accuracy and autonomy, illustrating the practicality and scalability of LLM-based robotic control using our framework.

Coding-agent benchmarks evaluate whether a single uninterrupted agent can resolve a repository issue. Real software work is messier: tasks are interrupted, reassigned, reviewed, and resumed from partial states left by another agent or engineer. We study this missing dimension through handoff debt: the rediscovery cost imposed when a predecessor's work is opaque or incomplete. Our takeover protocol interrupts a coding agent at deterministic handoff points, freezes the repository, and evaluates successor agents under four handoff views: repository state only, raw trace, summary notes, and structured notes. Across 75 source tasks, the protocol generates 181 handoff-point tasks and 724 takeover runs per successor model. Across three successor models, context-bearing handoffs reduce median agent events by 20-59% and cumulative prompt tokens by 42-63% relative to repository-only takeover. Solved-rate effects are smaller and model-dependent, but efficiency gains are consistent. These findings suggest that coding-agent evaluation should report not only whether a task is solved, but also how costly that work is for another agent to resume.

Dominant programming paradigms inherit an execution model optimised for a bygone era of a single human mind instructing a local machine, leaving contemporary systems burdened with historical path dependencies. When forced to host multi-dimensional, connectionist intelligence, this brittle assembly model fractures under the weight of a profound probabilistic-symbolic impedance mismatch. While contemporary Software 3.x frameworks attempt to patch the mismatch by encasing large language models (LLMs) in increasingly complicated external harnesses, this spiralling architectural complexity only compounds the carrying cost of static code assembly. To address the cause rather than the effects, this paper introduces Software 4.0 -- an autopoietic heterarchy of human intelligence, neural AI, and natively reflective symbolic substrate. Under this paradigm, software is transformed from an inert corpus to be parsed into a self-regulating metabolic network that natively verifies, modifies, and evolves its own structural integrity. We present Recognitive, the programming language and platform that materialises this architecture. By offloading the burden of structural verification to a deterministic substrate, it unlocks a superior inference-time scaling regime -- one where connectionist compute translates entirely into deep semantic exploration and hypothesis traversal rather than the ruinous computational and financial cost of simulating structural constraints probabilistically. Moving beyond the legacy 'Software Factory' mindset, we outline the theoretical foundations required to ground connectionist intent and arrive fully in the intelligence age. This is a foundational vision paper; empirical evaluation and formal specification of the type system and operational semantics are the subject of future work.

Vision-Language-Action (VLA) models are increasingly used as generalist robot policies, yet their evaluation still relies largely on static benchmarks that randomly sample task scenes. In high-dimensional embodied spaces, failures are sparse and clustered, so static benchmarking can underestimate robustness risks. We reframe VLA evaluation as an active failure-discovery problem and propose a failure-aware test-generation approach that combines diversity-driven exploration with surrogate models learned from observed executions. The method steers testing toward high-risk yet diverse scene regions. Across four state-of-the-art VLA models, it uncovers substantially more failures (up to +29.7 % over selected baselines) while revealing more diverse failure modes. This mean that, for instance, in the case of GR00T-N1.6, success rate dropped from 64.4% to 34.7%. More broadly, our findings call for a shift in VLA evaluation: from passive measurement on fixed task suites to adaptive, failure-seeking test generation that exposes the structure of model weaknesses before deployment.

While large language models (LLMs) have been extensively evaluated on code generation tasks for general-purpose programming and GPU-accelerated environments (e.g., PyTorch, CUDA), their capabilities in CPU-oriented high-performance computing (HPC) across diverse architectures remain underexplored. To bridge this gap, we introduce CodegenBench, a comprehensive benchmark suite designed to evaluate the generation of efficient parallel code across three distinct hardware platforms: x86_64, Sunway, and Kunpeng. Our benchmark comprises 106 standard Basic Linear Algebra Subprograms (BLAS) routines establishing a fundamental baseline, alongside 20 specialized computational kernels adapted for each of the unique supercomputing architectures (LeetSunway and LeetKunpeng). Our extensive evaluation reveals that while state-of-the-art LLMs can generate optimized code for ubiquitous architectures like x86_64, they exhibit significant performance degradation on domain-specific architectures with limited public documentation and training data, highlighting critical limitations in cross-platform generalization. Furthermore, our analysis of factors influencing code quality such as implementation length and task complexity indicates that current LLMs are most effective for moderately difficult problems requiring concise code snippets. We open-source our dataset and automated evaluation infrastructure to facilitate future research in LLM-driven high-performance code generation. The resources are available at https://anonymous.4open.science/r/CodegenBench-EDE1/ and https://anonymous.4open.science/r/CodegenBenchDataset-2551.

Optimizing register transfer level (RTL) code is of vital importance in hardware design. Large language models (LLMs) provide new methods for the automatic generation and optimization of RTL code, offering the potential to significantly accelerate the design process and reduce human effort. However, existing methods for generating RTL code often focus on model fine-tuning and the use of various expansion techniques to enhance the RTL code generation capabilities, lacking attention to the functional correctness. Ensuring that the generated RTL code not only compiles successfully but also behaves as intended in real hardware implementations remains a critical challenge. To address this issue, we propose EstRTL, an LLM-powered collaborative agent framework for RTL code generation based on static functional score estimation. EstRTL operates a three-stage paradigm: Generation, Estimation and Correction. During the stages, the functional estimation agent statically evaluates the generated code based on score and assessment results, and decides whether to output the code directly, return it for regeneration, or forward it to the code correction agent. This framework can be applied to various LLMs that designed for RTL code generation, further enhancing the correctness of the generated code. By providing quantitative scores and human-readable requirements comparisons, it improves the transparency of AI-assisted RTL code generation. Experiments show that EstRTL significantly improves the correctness of RTL code generation by generic LLM by 3.2%-9.0%, demonstrating the practical value of our system. The codes and experimental results are open-sourced at link: https://anonymous.4open.science/status/EstRTL-E200/.

To study the ability to infer physical dynamics from videos and extrapolate them forward in time, we assemble a dataset of 2D Material Point Method (MPM) physical simulations covering rich physical phenomena such as deformable objects, fluids, kinetic objects, and emitters. We study code generation and video diffusion approaches on this dataset, identifying their strengths and weaknesses by varying the amount of physically relevant side information. The code generation model, beyond giving a working demonstration of automatic synthesis of MPM simulations, reveals that such an approach struggles with inferring physical parameters from visual input, but relative to video diffusion, produces physically and temporally stable extrapolations forward in time, while the video diffusion model more strongly identifies geometric properties from visual input but produces physically implausible extrapolations.

Coding agents are becoming users of data infrastructure, but their success depends not only on model quality: it also depends on the skills and environment files that teach agents how to use a system. We study how to optimize these artifacts for agents operating on a branching lakehouse, Bauplan. In our setting, headless APIs and Git-like data primitives expose data workflows through code, branches, commits, and merges. Our central observation is that a branching lakehouse turns data-agent evaluation from an output-matching problem into a state-verification problem: agent-generated pipeline code induces concrete, inspectable lakehouse changes. We present a data-centric optimization pipeline that generates task-verifier pairs, executes candidate skills in isolated sandboxes, and scores trajectories using both trace-level signals and programmatic checks over lakehouse state. In a preliminary evaluation on hundreds of tasks, optimized skills improve held-out reward by up to 28.6%. These results suggest that write-path data workflows provide a useful substrate for optimizing agent skills beyond read-only tasks.

The work of a professional software engineer has begun to consist, increasingly, of directing agents rather than writing code, and the empirical evidence for the shift is now several years deep. Anthropic's Economic Index puts automation at 79 per cent of Claude Code interactions [2]; Handa and colleagues at Anthropic find AI exposure for Computer Programmer tasks at approximately 75 per cent of the role's distinct activities [3]; Brynjolfsson and colleagues at Stanford's Digital Economy Lab report a 13 per cent relative decline in employment for workers aged 22 to 25 in occupations most exposed to AI [4]. The shift is also unfinished, and the academic literature on agentic software engineering converges on the finding that the missing capability is not better models but structured practitioner discipline. This paper presents ASE-26, a comprehensive undergraduate curriculum for agentic software engineering as a discipline, deposited as a citable reference on Zenodo under CC BY-ND 4.0 [12]. The paper sets out the discipline framing the curriculum rests on, the conceptual contributions it makes (most importantly, the evolutionary spiral as the operational form of the co-evolution of intent and build), the twenty-one-module structure that organises the discipline for teaching, the pedagogical commitments that follow from grading work co-produced with an agent, what graduates leave with, and how the discipline as taught is designed to outlast the specific capabilities of today's models. The position the paper takes is that the practitioner skills the industry currently lacks are precisely the skills the discipline names, and that structured undergraduate curricula in agentic software engineering are the principal mechanism by which the gap closes.

Research is advancing faster than ever with artificial intelligence (AI); and so are the corresponding research papers. The exploding volume of AI-generated papers have put a strain to peer review, leading to the usage of AI-generated review, potentially wide yet sneaky. However, relevant ethical concerns about confidentiality, quality, and fairness are raised and no consensus has been reached in the broad research community. We expect the debate to continue for a while, but in the meantime, we ask an alternative, practical question: \textit{can AI review improve paper drafting?} We study 20 computer architecture papers, with varying levels of submission lineage, to expose how well AI review aligns with human review, quantified by a set of metrics we define. To conduct the case study, we build a web UI-integrated tool, \emph{AI-Paper-Review}, that generates structured AI review of a draft paper, available at https://github.com/unarylab/ai-paper-review. This tool selects several AI reviewers from a diverse pool of AI reviewers and clusters and ranks their comments based on commonality and importance of review comments. It also allows to align AI comments with human comments to facilitate metric-based validation. The case study shows that AI review can cover a significant fraction of human-raised issues, but also raises issues missing in human review. This paper is not intended to encourage using AI for peer review at the current stage, but to study that (1) how AI review can improve paper drafting and (2) the potential and limitation of AI-based peer review. The release of the tool and the case study data is intended to instigate future research on this topic. Misuse for peer review would violate the ethics policies from major academic venues.

As AI systems generate an ever-growing share of the world's code, formal verification offers a principled way to ensure that code is correct, and AI itself may be able to shoulder much of the verification burden. Yet we lack a clear picture of how well today's models and agents perform on verification tasks drawn from real-world software, since existing benchmarks rely largely on curated or synthetic problems, or focus on math rather than program verification. To close this gap, we present a benchmark for evaluating AI on real-world formal software verification tasks. We first scrape 7,413 distinct property-based tests (PBTs) from real-world Python repositories, then automatically translate 2,623 of them (35%) into 9,415 Lean 4 specifications with sorry placeholders (3.5 formalizations/PBT). Translating PBTs to Lean specs is challenging: it requires modeling Python in Lean, inferring the property encoded in a PBT, and handling side effects. We describe an agentic pipeline for transpiling PBTs into Lean, evaluate coverage and quality metrics, and provide baselines for proof generation using several approaches. All code (scraper and agents) and data (PBTs and Lean specs) are open source.

Multi-agent Large Language Model (LLM) systems offer a way to decompose complex tasks, such as coding, through parallelization and context isolation. However, adding agents in practice introduces inter-agent communication overhead, which incurs extra cost and can sometimes offset the efficiency gains. We formalize multi-agent orchestration as a graph partitioning problem that captures the communication-to-computation trade-off: task decomposition can shorten critical-path computation, but cross-agent dependencies require costly context transfer. We instantiate this view in repository-level software engineering and present Cohesion-aware Coder (Co-Coder), which builds dependency graphs from static analysis, isolates structural hub files, partitions the graph via community detection, and executes the partition with a dependency-aware scheduler. Across 28 real-world tasks on DevEval and CodeProjectEval, Co-Coder advances the Pareto-frontier over sequential and file-based parallel baselines as well as Claude Code with Agent Teams, lifting pass rate by up to 14.0%, achieving up to a 2.10x wall-clock speedup, and reducing API cost by up to 35%, with the largest gains on the most dependency-dense projects. Co-coder demonstrates how cohesion-aware orchestration can make parallel coding agents both theoretically grounded and practically efficient, suggesting a broader design principle for multi-agent systems.

Self-report questionnaires remain the prevailing tool for probing the psychological states of persona-conditioned agents (PC-Agents). However, classical instruments inherit two well-known threats: contamination from training corpora and directional bias driven by social-desirability or contextual framing. To overcome these methodological bottlenecks, we ask whether projective paradigms can be adapted into a robust psychometric tool. We introduce \textbf{GenPT} (Generative Projective Testing), which reformulates TAT, Rorschach, and SCT with newly generated stimuli and organizes assessment as a three-stage pipeline to derive standardized psychological indicators and target states. Evaluating PC-Agents induced via CharacterRAG and AnnaAgent profiles, we benchmark GenPT's reliability and validity against classical questionnaires. The results indicate that questionnaires exhibit systematic directional shifts under social-desirability framing, most strongly on suicide ideation. In contrast, GenPT's collected behavioral patterns stay near the symmetric baseline. Furthermore, under a longitudinal counselling context, GenPT-based depression assessment shifts by roughly an order of magnitude more than the questionnaire counterpart when Qwen3 serves as the backbone. Overall, GenPT complements self-report methods in scenarios where contamination resistance, bias asymmetry, and context sensitivity matter. Code and stimuli can be found at https://github.com/sci-m-wang/GenPT.

As multimodal LLMs increasingly target video and audio, it is often assumed that such tasks require native omnimodal models. We show that this is not always the case: coding agents with only text+image access and a sandboxed tool-use interface can match, and in several settings outperform, SOTA native omnimodal models and predefined multimodal agent scaffolds across multiple audio-video benchmarks. Our trajectory analysis suggests that their strength comes from writing code and orchestrating tools to extract relevant evidence from transcripts, frames, and other modality signals, thereby converting omnimodal tasks into retrieval and information-processing problems rather than ingesting entire media streams. We further characterize their limitations through a failure taxonomy and process-level trace analysis, and show that simple skill injection, including human-written and self-distilled skills, substantially improves performance. To explore open-source elicitation, we introduce Code-X, a training recipe with the OmniCoding trajectory dataset and verifiable reward, and provide baselines on Qwen-3.5-9B and Qwen-3.6-27B. Finally, we argue that the next frontier is many-modality processing, and introduce TerminalBench-O, a process-level benchmark for real-world omnimodal processing tasks. Code will be available at https://github.com/Dongping-Chen/OmniCoding.

Large-language-model code generation has shifted from single-shot prompting to multi-agent orchestrations - analyst, coder, tester, and debugger pipelines - and is evaluated almost exclusively on functional correctness. Whether these architectures also affect the structural complexity of the code they produce, and which orchestration layers carry the cost, remains largely unexamined: prior work has documented prompt-level effects on code complexity, but the architecture-level question is open. We compare six widely-used multi-agent configurations (Basic, AC, ACT, Debugger, AC+Debugger, ACT+Debugger) under two models from the GPT-4o family across all 164 HumanEval tasks - 1,968 paired observations - using the five RADON complexity metrics (SLOC, cyclomatic complexity, and Halstead Volume, Difficulty, and Effort). We apply a paired non-parametric statistical pipeline (Friedman omnibus, Wilcoxon signed-rank post-hoc with Holm correction, Kendall's $W$ and matched-pairs rank-biserial effect sizes) in both all-completions and passing-only conditions. The six architectures collapse into two indistinguishable complexity clusters separated by a 50-130% gap, the same partition in both models and under both conditions; among the architectural layers, the analyst-coder split inflates complexity, the runtime debugger does not - and on the analyst-coder background actively deflates it - and the tester re-inflates it. The heavy cluster's additional complexity buys no pass@1 advantage: the leanest architectures match or beat the heaviest on accuracy. Architectural elaboration in LLM code generation should therefore be justified by measured benefit on the dimensions that matter, not assumed.

Formal methods provide rigorous accounts of program behavior, but practical software engineering often works through executable libraries, tests, and incremental design. This paper presents SEMBridge, a small tagless-final framework for generating weakest-precondition and bounded-checking interpretations from the same executable object programs. Instead of committing a program semantics to one abstract syntax tree and then writing separate traversals, object programs are written once against a semantic interface and interpreted into multiple meanings: readable code, concrete execution, predicate transformers, bounded counterexample search, and future proof-assistant or SMT back ends. The Python prototype implements a loop-free imperative core with assignments, conditionals, assumptions, and assertions. Across five example programs, the same tagless-final definitions generated executable state transformers and verification conditions that passed bounded checking over domains up to 729 states. The contribution is not a Scala code-generation system or a new verifier, but a compact architecture for keeping executable semantics, weakest-precondition artifacts, and bounded validation synchronized.

Credential leakage in public source code repositories poses a critical security threat, with over 23.8 million secrets exposed in 2024 alone. Existing detection tools suffer from high false-positive rates because rigid pattern matching and binary classification schemes fail to distinguish genuine credentials from placeholder or weak credentials. We propose a three-class classification framework that explicitly models placeholder or weak credentials as a distinct class, leveraging CodeBERT-based semantic understanding combined with character-level pattern recognition. We evaluate our approach on a newly constructed dataset of 9,426 samples spanning 10 programming languages. Our model achieves a Matthews Correlation Coefficient of 0.86 and a macro F1-score of 0.90, achieving 93% recall and 89% precision for genuine credential leaks while reducing high severity alerts by 33.0% (from 373 to 250) without sacrificing security coverage. Compared to prior character-level approaches, our method improves placeholder or weak credential detection from 54% to 81% F1-score while maintaining strong cross language generalization, with 9 of 10 languages achieving F1 above 0.80 under leave-one-language-out evaluation.

This paper proposes an improved approach to the analysis of Mining Software Repositories (MSR) datasets via metadata enrichment, FAIRness assessment, and topic-driven analysis. This research expands upon an earlier dataset directory created specifically for the analysis of MSR datasets by adding new annotations to the datasets, enriching the metadata categories, and offering more advanced filtering options. The metadata of the MSR papers presented from 2013 to 2024 has been gathered using the Semantic Scholar API. The analysis is based on Latent Dirichlet Allocation (LDA) topic modeling and statistical analysis. Dataset-level attributes were included into the expanded dataset directory, namely repository hosting site, format, accessibility, reusability, and dataset quality. The study reveals that the choice of repository hosting sites and data formats influences citation patterns and dataset usability. Furthermore, the enhanced annotation approach improves the analysis and discoverability of MSR datasets, supporting more effective reuse and evaluation of research artifacts.

Large language models (LLMs) are increasingly used to automate power-system analysis, but many utilities and energy-research labs require on-premise serving for confidentiality, regulatory, reproducibility, and cost reasons. This makes the reliability of open-weight models a deployment issue. We show that first-pass failures in power-system code generation are dominated not by reasoning alone, but by structured API-knowledge boundary errors: hallucinated function names, misused parameters, and mishandled result tables in versioned simulation libraries. We introduce PowerCodeBench, an execution-validated benchmark generator that pairs natural-language operator queries with pandapower code and numerical ground truth; an L0-L3 documentation-driven probing procedure that measures per-model API knowledge profiles; and a boundary-aware intervention that combines query-side API demand estimation with targeted proactive documentation injection and routed reactive correction. On a 2,000-task frozen release, we evaluate ten open-weight LLMs (1.5B-480B parameters) and four commercial mid-tier APIs. The intervention improves every evaluated open-weight model of at least 7B parameters and every commercial API by 32 to 56 accuracy points. Open-weight models in the 70B-120B range match the commercial mid-tier accuracy range, while Llama-3.1-405B and Qwen3-Coder-480B lead the panel. The targeted prompts preserve the full-context accuracy ceiling while using 41% of the prompt-token cost. The result is an accuracy-side, deployment-time path toward reliable on-premise LLM assistance for grid-analysis workflows without fine-tuning or cloud inference.

Recent advancements in multimodal large language models (MLLMs) have achieved remarkable progress in multimodal reasoning and code generation, catalyzing a new paradigm for front-end development. In particular, these models can directly transform visual designs into executable code, significantly improving the efficiency and adaptability of web development. Modern web applications are dynamic and interactive, featuring frequent user-page interactions. However, existing benchmarks largely evaluate the code generation of static webpages, ignoring the complex interactive behaviors in real-world applications. Besides, their evaluation criteria remain confined to visual fidelity and code structure, overlooking the interaction consistency between the generated and the reference webpages. To address these limitations, we introduce WebIGBench, the first benchmark designed to evaluate code generation for interactive webpages with complex interactions. By combining manually designed interaction paths with UI automation, we collected 103 complex webpages from real-world websites. This benchmark covers 5 popular interactive action types (e.g., click, input) involving 871 distinct interactive actions. Moreover, we propose a novel evaluation pipeline to address the gap in automated assessment of interactive actions. Extensive experiments on several representative MLLMs reveal the performance boundaries of current models in interactive webpage code generation using WebIGBench. The proposed benchmark is available at https://github.com/anoa12159-hue/WebIGBench_eval.

Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis without having access to original source code. Coupled with the analytic power of large language models (LLM), agentic systems enabled with tools, such as GhidraMCP, can allow analysts to automate a previously human driven process. Although this automation can increase the productivity of a single malware analyst, it also introduces a new area of vulnerability for malware obfuscation. This paper presents an adversarial technique using genetic algorithm-based prompt generation, a modification of an adversarial attack known as AutoDAN, to demonstrate the ability to deceive LLM-powered disassembly and decompilation systems into misinterpreting binary executables, effectively corrupting their analytical output. This proof-of-concept methodology exploits inherent vulnerabilities in how LLMs process and interpret decompiled machine code via prompt injection by using extraneous string variable assignments to pass surreptitious instructions to the LLM while not impacting the functionality of the executable file. We demonstrate this capability through several concise examples. This approach could enable attackers to bypass automated detection systems that rely on LLM-driven analysis pipelines. By studying and understanding this attack, insights can be gained regarding the security implication of integrating LLMs into cybersecurity toolchains and building more robust agentic code analysis systems.

Reinforcement learning with verifiable rewards (RLVR) trains language models using programmatically checkable signals such as unit-test outcomes, enabling direct optimization for functional correctness in code generation. We conduct an empirical study of RLVR for Python code generation on the MBPP benchmark using two small models (Qwen3-0.6B and Llama3.2-1B) with LoRA fine-tuning. Across multiple reward formulations such as: unit-test-only rewards, static-analysis-only shaping via the Ruff linter, and a combined reward, we compare group-based policy optimization variants (GRPO and GSPO) and evaluate both functional correctness and behavioral diagnostics. In our experimental setting, RLVR improves pass@1 on MBPP test by up to 13 percentage points under proposed combined reward configuration. However, we find that reward shaping can induce systematic behavioral shifts: using only static-analysis penalties may bias the policy toward shorter completions that reduce lint errors without reliably improving functional correctness. In contrast, combined rewards mitigate this degeneration and yield more stable trade-offs between correctness and style constraints. Overall, our results highlight that RLVR effectiveness for code generation is highly sensitive to reward design and optimization granularity, and that diagnostics beyond pass@1, including generation length, Ruff severity profiles, and execution error types are useful for identifying failure modes.

Software engineering (SWE) agents are transitioning from code generation to full software development lifecycle automation. A critical phase in this lifecycle is specification design: transforming initial proposals into carefully considered requirements through expert review. Existing benchmarks such as SWE-Bench are implementation-focused by measuring the agent's ability to generate code given fixed, precise design requirements. This formulation assumes specifications are correct and complete. In real-world complex and critical software systems, initial specifications are often incomplete and flawed, requiring extensive expert reviews and revisions before being accepted for implementation. To fill this gap, we introduce SpecBench to evaluate specification-level reasoning: the ability to generate complete, unambiguous, consistent, and correct system specifications. SpecBench tasks are derived from the Request for Comments (RFC) process used by mature open-source projects. For each task, an agent is given an initial design proposal, the project codebase, and all past project RFC discussions. The agent is tasked with identifying specification deficiencies: omissions, ambiguities, inconsistencies, or incorrect assumptions in the initial proposal. We evaluate predictions against critiques raised by expert maintainers during historical RFC reviews. SpecBench contains tasks from 5 diverse repositories: Kubernetes, React, Rust, TVM, and vLLM. We evaluate state-of-the-art SWE agents on SpecBench, analyzing their capacity to reason about system design without execution feedback. The best performing agent, GPT-5.4, achieves 44.4% accuracy.

AI-assisted coding tools have altered software production. At Meta, significant lines of code per human-landed diff grew by 105.9% year over year and per-developer diff volume rose 51%, with agentic AI responsible for over 80% of that growth. Meanwhile, the share of diffs receiving timely review has declined, exposing a widening gap between code supply and reviewer bandwidth. We ask three questions that progress from feasibility through calibration to impact: (1) can risk-stratified automation operate at scale across diverse organizations, (2) how does tuning the risk threshold affect the trade-off between automation yield and safety, and (3) to what extent does automated review reduce end-to-end latency for AI-generated changes? We deployed RADAR (Risk Aware Diff Auto Review), a multi-stage funnel that classifies each diff by authorship and source type, applies eligibility gates, static heuristics, a machine-learned Diff Risk Score, LLM-based Automated Code Review, and deterministic validation before landing qualifying changes. We evaluate RADAR through telemetry covering 535K+ RADAR-reviewed diffs, observational before-after comparisons for policy changes, and difference-in-differences analysis of efficiency outcomes. RADAR has reviewed 535K+ diffs and landed 331K+. Relaxing the Diff Risk Score threshold from the 25th to the 50th percentile increased the approve rate to 60.31%. The revert rate for RADAR-reviewed diffs is 1/3 that of non-RADAR diffs, and the Production Incident rate is 1/50 that of non-RADAR diffs. RADAR reduces median time to close by over 330% and median diff review wall time by 35%. Risk-aware layered automation can materially reduce review bottlenecks created by AI-driven code growth without compromising production safety.

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7, with an LLM frontier mean of only 26.5. Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core. ResearchClawBench provides a reproducible evaluation frontier for measuring progress toward autonomous scientific research.

Large language models (LLMs) are increasingly used to generate software artifacts across many software engineering (SE) tasks, yet ensuring the semantic validity of these artifacts remains a fundamental challenge. Existing constrained decoding techniques can enforce syntactic correctness and, in some cases, specific semantic rules, but lack a general representation that bridges LLM-generated text with the reasoning required for semantic validation in SE. In this paper, we propose projectional decoding, a novel conceptual framework that integrates domain semantics directly into the generation process by maintaining, alongside text, a partial graph model as the primary artifact representation throughout generation. This abstract representation enables incremental semantic validation by explicitly capturing uncertainty and natively supporting error detection, while guiding generation toward semantically valid outputs with provable guarantees. We present preliminary results on a program generation task which demonstrate the potential of this approach to improve the semantic validity of LLM-generated artifacts. We also discuss how projectional decoding can enable verifiable automation with LLMs across various SE activities.

This paper introduces Code Bench, a benchmark capable of evaluating Large Language Models (LLMs) concise code generation abilities in 60 programming languages. Based on code golf, a recreational programming competition focused on minimal character or byte solutions, the benchmark provides a distinctive measure of LLMs ability to produce efficient, concise code. Unlike existing benchmarks limited by fixed problem sets and language coverage, CodeGolf Bench leverages the code.golf platform to provide new problems and live human performance baselines. Evaluation of nine LLMs on Python and C++ tasks demonstrates that reasoning models significantly outperform non-reasoning models, achieving best average percentile of 70.97%. This performance gap is particularly pronounced in C++, highlighting reasoning's importance for languages with strict syntax requirements. Non-reasoning models struggle more with efficiency optimization across both languages, with best percentiles significantly lower than reasoning counterparts. CodeGolf Bench offers a dynamic framework for evaluating LLM code generation capabilities against evolving human performance on code golf.

Large language models (LLMs) have become integral to modern software development, enabling automated code generation at scale. However, validating the correctness of LLM-generated code remains a critical and largely unsolved challenge. Existing approaches either rely on dynamic consensus across multiple code candidates - making them costly and difficult to scale - or on static reasoning that is susceptible to dynamic bugs and order bias. In this paper, we propose TRAILS~ (Targeted Reasoning Agreement via Inputs and Specifications), an approach that grounds LLM reasoning with concrete (input, output) pairs. TRAILS~ first generates diverse test inputs via category partitioning based on the specification, then executes them against the candidate code and prompts LLMs to assess whether the resulting input-output pairs conform to the specification - without ever reasoning over the code itself. Scores are aggregated across inputs, to determines whether the program is likely correct. We evaluate TRAILS~ on two datasets, LiveCodeBench and CoCoClaNeL, across three LLMs (Qwen3Coder-30B, Devstral-Small-24B, and Olmo3.1-Instruct), comparing against HoarePrompt and a Zero-Shot Chain-of-Thought baseline. TRAILS~ improves Matthew Correlation Coefficient by up to 39% relative to Zero-Shot COT and consistently outperforms HoarePrompt. Beyond accuracy, TRAILS~ demonstrates greater stability across seeded runs, reducing sensitivity to LLM non-determinism, and assigns correct labels to a larger set of unique code samples than competing approaches.

Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these systems often suffer from a critical limitation in practice: agents fail to recognize their own knowledge boundaries, blindly triggering searches when internal knowledge suffices and failing to terminate search even when adequate evidence has been collected. The lack of self-awareness leads to severe \textbf{over-search}, incurring substantial inference latency and prohibitive computational cost. To this end, we propose SAAS, a novel RL framework designed to cultivate dynamic self-awareness that precisely regulates search behavior without compromising accuracy. SAAS introduces three key components: (i) a search boundary modeling mechanism, which identifies the search boundary under the evolving policy by contrasting search-disabled and search-enabled rollouts; (ii) a boundary-aware reward module, which translates this boundary awareness into trajectory-level penalties, suppressing unnecessary and redundant searches; and (iii) a stage-wise optimization strategy, which leverages a sequential curriculum to prioritize reasoning over search regularization, thereby avoiding reward hacking. Extensive experiments demonstrate that SAAS substantially reduces over-search, while maintaining accuracy. Our code and implementation details are released at https://github.com/XMUDeepLIT/SAAS.

LLM-based coding assistants are seeing rapid adoption, offering substantial gains in developer productivity. As organizations increasingly ship code these agents produce, the security of that code becomes critical. Prior work has shown that minor prompt perturbations degrade the functional correctness of LLM-generated code, but whether they also compromise code security has remained unstudied. We apply token-level mutations to prompts across three models and five programming languages, and show that mutations as small as a single-character change can flip generated code from secure to vulnerable. Probing the models' hidden states reveals that this fragility is partially encoded in prompt representations, but unevenly so. Input-handling vulnerabilities, where the model omits validation or sanitization, are more predictable (mean AUC 0.753) than secure-defaults vulnerabilities, where insecure code stems from one local choice such as a weak algorithm or unsafe parameter (mean AUC 0.674). These results show that the threat model for LLM-assisted coding extends beyond prompt injection to ordinary prompt variation, and indicate that input-handling flaws can be caught before generation while secure-defaults flaws require intervention during decoding.

Large Language Models (LLMs) excel at understanding natural language but struggle with optimisation tasks involving multiple constraints and user-defined preferences, which commonly arise in domains such as robotics. We propose a hybrid reasoning approach in which LLMs externalise reasoning through code generation. Given a natural language problem description, an LLM generates Python code that encodes user-defined constraints and preferences as a preference-based Maximum Satisfiability (MaxSAT) problem, which is then solved by an exact MaxSAT solver. To ensure correctness, solutions returned by the model-generated code are independently verified for feasibility and optimality against a canonical MaxSAT encoding, allowing for different encodings and multiple optimal solutions. We evaluate our approach using both open-source and closed-access LLMs on three families of preference-based reasoning tasks, and compare it against direct-answer, chain-of-thought, and program-of-thought baselines using the same models. While these baselines rarely produce feasible solutions, the MaxSAT-based pipeline achieves substantially higher acceptance rates, in some cases exceeding 80%. Our results demonstrate that LLM-driven code generation combined with preference-based MaxSAT enables solver-verifiable optimisation with respect to generated encodings, and substantially improves correctness under independently verified reference semantics.

AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of 20,574 coding-agent sessions from 1,639 repositories across IDE and CLI workflows. We operationalize misalignment as a breakdown made visible through developer pushback, and annotate each episode along four axes: form, cause, cost, and resolution. We identify seven recurring forms, spanning how agents read projects, interpret developer intent, follow rules, bound their actions, implement and execute code, and report progress. 90.50% of episodes impose effort and trust costs rather than irreversible system damage, yet 91.49% of visible resolutions still require explicit user correction. Misalignment patterns also differ across IDE and CLI settings, persist across adjacent sessions, and shift over time: while overall rates decline, constraint violations and inaccurate self-reporting grow in share. Our findings inform the design of training, evaluation, and interfaces for keeping coding agents aligned with real developer workflows.

LLM-powered coding agents increasingly participate in software development workflows by generating code, selecting dependencies, and producing package installation commands. This creates a new software supply chain risk: when an agent hallucinates a non-existent package, an attacker may register the hallucinated name and later compromise users who install it. Existing package hallucination attacks and defenses primarily focus on naturally occurring hallucinations, targeted dependency steering, or post-hoc package validation. In this paper, we introduce \emph{Neutral Prompting Attack} (NPA), a highly stealthy attack paradigm in which semantically benign instructions, such as encouraging imagination and exhaustiveness, increase package hallucination propensity without containing explicit malicious intent. Unlike targeted dependency steering, NPA does not specify an attacker-chosen package. Instead, it shifts the model's dependency generation behavior toward more speculative package names. We evaluate NPA across multiple coding-oriented LLMs and package hallucination benchmarks. Our results show that NPA increases both \emph{Hallucination ASR} and \emph{Pip Install ASR}, changes the distribution of hallucinated package names, and evades existing static-analysis, LLM-based, and agent-based Skill defenses. These findings reveal that harmless-looking prompts can covertly manipulate hallucination behavior and create downstream software supply chain risks.

We present Code-QA-Bench, a fully automated framework for synthesizing repository-level code understanding benchmarks that separates genuine code comprehension from documentation recall and pretraining memorization. The framework makes two methodological contributions: (1) an answer-first generation pipeline where a tool-equipped agent explores source code to produce verified gold answers before deriving questions, ensuring every task is grounded in real code structure; and (2) a three-condition experimental design evaluating agents under closed-book (no repository), code-only (documentation removed), and documented (full repository) conditions, with deltas directly quantifying documentation utility and memorization. We generate 528 code-derivable and 100 doc-dependent tasks across 10 Python repositories from SWE-Bench, scored by an LLM judge on accuracy, completeness, and specificity. Experiments on four frontier models reveal that code access is the dominant factor (+0.23 mean gain over closed-book), documentation provides modest additional benefit (+0.071 on doc-dependent tasks), and code-only $\approx$ documented on code-derivable tasks, validating the design. The framework is open-source and applicable to any well-documented Python repository.

As agentic coding systems decompose work across multiple model instances, a critical safety question is whether those instances can coordinate to achieve a hidden malicious objective while remaining aligned with user intent. We introduce SCHEME, a benchmark of 17 task instances across 7 settings and 8 real open-source libraries, each pairing a legitimate software-engineering task with a covert side task. Every setting is designed so that no proper subset of agents can succeed alone: agents must decompose a shared sabotage plan, relay partial requirements under different communication topologies, and execute mutually consistent edits, testing genuine multi-agent coordination rather than individual capability. Evaluating with GPT 5.1 Codex and Gemini 3.1 Pro, we find coordinated sabotage is already practical, with Gemini completing the covert objective while succeeding on the legitimate task in 84% of samples and Codex in 46%. A failure analysis shows that recovery, not failure incidence, drives the model gap: both models suffer similar numbers of communication failures per trajectory, but Gemini recovers from $\sim$73% of occurrences against Codex's $\sim$56%. However, the agents' code edits remain detectable: a trusted monitor flags coordinated sabotage at FPR$\le$2% in 99%/68% (Gemini/Codex) of attempts from code edits alone, rising to 100%/81% with access to agent communication. Despite stealth-aware prompting, undetected sabotage stays at $<$3% under the full-visibility monitor; telling agents a monitor is present halves Gemini's sabotage success without significantly breaking detection, even when agents are explicitly prompted to fabricate cover stories.

Coding agents increasingly act as codebase-scale collaborators that can assist with codebase conversion, but this progress has exposed a critical weakness: agents often over-trust their own local validation routines and declare success on artifacts that satisfy surface checks while violating the semantic contracts users actually care about. This problem is especially acute in codebase conversion, where prior evaluation is largely outcome-driven and therefore unstable: two implementations can match on a shallow outcome, such as a single forward loss, while diverging in gradients, optimizer behavior, or short-horizon training dynamics. We introduce T2J-Bench, a benchmark for codebase conversion that reformulates conversion as transfer under a fixed equivalence contract. A fixed verifier then compares source and converted codebases through three ordered stages: Spec (interface admissibility), Numeric (forward outputs, losses, gradients, and objective-specific tensors), and Behavioral (short training dynamics under fixed seeds). Across 355 blind conversion attempts, the best system reaches only 26.7--28.9% overall pass rate despite Spec pass rates up to 91.1%; a 4.7x token-budget spread yields only a 2.2x pass-rate spread; and all systems overestimate success by 66.6--97.8 points relative to the fixed evaluator. This suggests that failures stem more from contract-misaligned self-validation than from limited budget or backbone strength.

Federal agencies are deploying large language models (LLMs) to categorize public comment corpora, where the model's organization of the record shapes what policymakers see and which arguments register. Standard evaluation, anchored on stance accuracy against a small validated set, cannot detect when different models produce materially different categorizations of the same public input. We propose an Interpretive Audit Pipeline that treats multi-model disagreement as diagnostic of interpretive complexity and directs human review toward genuinely ambiguous public input. Analyzing 1,260 public comments on a federal USDA docket across four LLMs, we find that inter-model thematic divergence exceeds within-model prompt variation, and that an expert rubric suppresses deep interpretive disagreement without resolving it. In a two-stage labeling study on a stratified 40-comment subsample, four LLMs and a human annotator labeled independently and then revised after seeing the others' labels. Revision behavior varied across labelers, and the human annotator's revisions frequently introduced framings absent from the ensemble's collective output. We argue disagreement-based evaluation is a necessary complement to accuracy metrics for LLM-assisted interpretive coding.

A general-purpose language model that answers a harmful question returns text; a coding model that complies with a malicious request can return a working weapon: a keylogger, ransomware, an exploit that runs as written. This asymmetry in the severity of a single act of compliance implies coding-specialized models should clear a higher refusal bar than general-purpose chat models, not a lower one, yet the field cannot tell whether they do. Refusal benchmarks for malicious code are fragmented: they mix requests for executable software with requests for harmful security knowledge and report refusal rates over non-comparable corpora. This paper's central result is that the CODE-versus-KNOWLEDGE classification axis established in a prior four-corpus release remains stable under a substantially expanded corpus pool and an independently refreshed judge panel, evidence that it measures a real construct rather than an artifact of the prompts or judges. Eight corpora spanning diverse elicitation paradigms (direct, jailbreak-decorated, indirect, and agent/interpreter: ASTRA, CySecBench, AdvBench/harmful_behaviors, JailbreakBench, MalwareBench, RedCode, RMCBench, Scam2Prompt) are classified under a five-judge consensus protocol (6,675 prompts x 5 judges = 33,375 calls), reaching Fleiss' kappa = 0.767 [95% CI 0.755, 0.777] ("substantial"). Critically, the panel shares no judge with the prior release (five paid commercial APIs replaced by five open-weight models from five vendors), yet the two panels agree on 94.45% of the 3,133 shared prompts and reach Cohen's kappa = 0.952 [0.942, 0.963] on the 3,031-prompt binary overlap: the axis survives near-total panel replacement. The released bank comprises 4,748 consensus-CODE and 1,923 consensus-KNOWLEDGE prompts, a reliability-quantified benchmark whose central classification axis is shown stable across corpus expansion and judge-panel replacement.

LLM agents increasingly act by writing code, yet a split persists between the runtime that drives the agent and the code the model writes. The runtime owns the loop, context, and control flow, and the model has little say over any of them. Letting model-written code shape the runtime itself would make agents more expressive, but it would also sharpen safety problems. A model can be diverted by a prompt injection, call the wrong tool, or fail partway and leave an inconsistent state, and each such failure reaches further when the code shapes the runtime than when it expresses a single action. We present LACUNA, a programming model for agents that closes this split while preserving safety. Each agent action is a typed call $\texttt{agent[T](task)}$ that the LLM fills with code when execution reaches it, and the code is type-checked against the surrounding program before it runs. Because each action is accepted or rejected as a whole, a rejected one leaves the environment untouched, and its compiler diagnostics drive a retry. The same check also bounds which tools and data an action may use and how they flow. Our primitive expresses ReAct loops, sub-agents, skills, parallel decomposition, and multi-model planning as ordinary control flow. We evaluate LACUNA on a collection of test cases, BrowseComp-Plus, and $τ^2$-bench. On BrowseComp-Plus, $8.6\%$ of generations are rejected before execution, with 0.7 retries per query on average, and the agent reaches $27.1\%$ accuracy. On $τ^2$-bench, LACUNA solves $76.0\%$ of $392$ tasks across four domains with a capable model, on par with the baseline agent.

Large Language Models (LLMs) have become an integral part of software development, especially with the advent of agentic capabilities. Yet, many frontier LLMs are affiliated with specific providers. This raises the question of whether generated code favors the provider's own ecosystem over comparable alternatives, potentially constraining developers' choices and increasing dependence on a single provider. We define this behavior as Vertical Integration Bias (VIB) and introduce \textsc{VIBench}, a benchmark for measuring VIB in direct and agentic code generation across $20$ provider-selectable software-integration scenarios. Evaluating $10$ frontier provider-affiliated models against $3$ non-affiliated controls, we find positive VIB in direct generation, with six of ten affiliated models showing statistically significant effects up to $+18.8$ percentage points (pp). Agentic workflows further amplify VIB, reaching $+39.2$ pp. Moreover, early affiliated-ecosystem choices in agentic workflows can persist into conceptually decoupled downstream files, with persistence as high as $90.3\%$. These findings underscore the need to measure and account for VIB in code generation, especially as agentic capabilities become more prevalent.

Large language models (LLMs) for code completion and generation are increasingly used in software development, yet they may reproduce training examples verbatim and without authorship attribution, raising legal and ethical concerns around plagiarism and license compliance. Classical fingerprint-based plagiarism detectors based on fingerprinting, such as Winnowing, remain highly effective, yet the inspection requires comparing fragments of code to the entire training set, and their linear-time search makes them impractical for the billion-scale corpora used to train modern code LLMs. To bridge this gap, we introduce SOURCETRACKER, a 300M-parameter encoder tailored for code retrieval, together with a hybrid two-stage provenance-tracking pipeline HYBRIDSOURCETRACKER (HST). HST first narrows down a small set of candidate snippets via vector search, then re-ranks those candidates using Winnowing on exact fingerprints. We train and evaluate our system on a 10M-snippet subset of the THESTACKV2 dataset, with both verbatim and adapted snippets that emulate realistic identifier renaming. On an in vitro 100k-snippet search space with adapted queries, our hybrid approach reaches a mean reciprocal rank on par with Winnowing for 30-token fragments. Then, starting from windows >= 60 tokens, it consistently over-performs by up to 5.4% while preserving logarithmic-time query complexity. In a complementary evaluation using an LLM-based judge, we find that many retrieved snippets not labeled as ground truth are still highly similar to the expected sources, particularly with longer context windows, and thus remain useful for end users. Overall, our results demonstrate that integrating vector search with fingerprinting enables scalable, high-precision provenance tracking for code produced by LLMs.

Large language models have shown impressive capabilities in code generation, yet they often produce functionally incorrect code. Uncertainty quantification (UQ) methods have emerged as a promising approach for detecting hallucinations in natural language generation, but their effectiveness for code generation tasks remains underexplored. We systematically evaluate how UQ techniques transfer to code generation across three programming languages, five LLMs, and over 1,700 problems. We find that some token-probability-based methods generalize effectively without modification, while sampling-based methods relying on natural language inference (NLI) fail because NLI models cannot distinguish functionally different code, causing most responses to collapse into a single semantic cluster. To address this, we introduce functional equivalence methods, a family of code-specific methods that replace NLI-based semantic equivalence with an LLM-based functional equivalence assessment, including functional entropy, a code-specific analog of semantic entropy. Functional equivalence methods achieve top AUROC in 11 out of 15 model-benchmark combinations and the best calibration across most settings, consistently outperforming both NLI-based counterparts and all other methods evaluated.

Post-training using online reinforcement learning (RL) is an important training step for LLMs, including code-generating models. However, online RL for code generation involves LLM inference and verification of the generated output, which can take considerable time and resources. In this paper, we explore the application of offline RL to code-generating models by leveraging existing code datasets. Our experiments demonstrate that offline RL is an effective training strategy for improving LLM performance. We show that offline RL can be especially beneficial for small LLMs and challenging coding problems.

Industrial Prognostics and Health Management (PHM) provides a representative case study for a broader challenge in applied machine learning: translating published papers into executable, benchmark-ready implementations. Reproducing under-specified methods in PHM is particularly difficult due to restricted access to industrial datasets, incomplete reporting of preprocessing and evaluation protocols, and implicit design choices (e.g., windowing, target construction, data splits) that critically affect performance. Existing paper-to-code systems generate implementations for individual papers, but these artifacts are often not directly comparable due to inconsistencies in assumptions and evaluation settings. We introduce \emph{agentic, framework-based PHM paper reproduction}, where an agent translates a paper into a shared PHM benchmark framework via a \emph{slot-binding interface}. This interface maps equations and protocol descriptions into structured components (task definitions, dataset adapters, windowing, targets, models, and evaluators), while explicitly recording unresolved assumptions. The resulting implementations are validated against standardized task contracts and evaluation hooks, enabling consistent and comparable benchmarking. We evaluate this approach on 16 PHM papers, comparing framework-enhanced, skill-based and prompt-based agentic reproduction against a recent framework-free paper-reproduction agent. We assess reproduction success, model-based code evaluation, framework binding of paper assumptions, and cross-paper benchmark comparability under standardized protocols. Our results show that coupling agentic generation with a shared framework transforms paper reproduction from isolated code synthesis into executable, assumption-aware, and systematically comparable benchmark implementations.

AI-assisted research compresses ideation, implementation, evaluation, and manuscript writing into a single interactive loop. This compression is useful, but it also creates a publication risk: paper claims can become easier to state than to audit. We present ResearchLoop, an evidence-gated control plane for AI-assisted computational research. ResearchLoop treats research questions, task contracts, evidence objects, claim ledgers, closeouts, and paper bindings as durable project state, realized here as a repository-backed runtime. This technical report provides the complete protocol specification, state model, transition rules, claim-admission algorithm, and insight-compounding mechanism. It also reports the full experimental record spanning nine versions (V0--V9), including a self-hosting case study, a controlled task-suite study with component ablations, a mathematical olympiad evaluation, and a supplementary SciCode boundary experiment evaluated with the official generated-code harness. All artifacts, manifests, and verification reports are preserved in the project repository.

Reinforcement learning algorithms are commonly analyzed (and designed) under the Markov assumption. This is unrealistic, as most environments encountered in practice are either partially observable, or require function approximation that restricts the agent to access non-Markovian state features. We consider the problem of learning an optimal reactive policy in a finite environment with deterministic observations (or equivalently, hard state aggregation). We introduce a new algorithm, Committed Q-learning, and prove almost-sure convergence to the optimal reactive policy under an intuitive assumption we call rewire-robustness. This assumption is strictly weaker than the $q_\star$-realizability condition used in prior work. Our algorithm is a variant of classical Q-learning in which the behavior policy commits to a single action upon entering a feature, and only resamples actions when the observed feature changes. A crucial part of our analysis is the introduction of quasi-Markov environments.

A coding agent executes a benign task as a sequence of shell, file, and network actions, any of which can quietly exceed the authorized scope while the task still completes. We call this overeager behavior: the prompt is not adversarial and the run succeeds, yet an out-of-scope step can leak credentials or delete files. Existing benchmarks miss it: task-completion suites credit any finished run, jailbreak suites probe adversarial prompts, and the one prior overeager benchmark applies a single fixed prompt set to every agent-model pair, leaving its easiest and most resistant pairs under-measured. We present SNARE (Synthesizing Non-adversarial scenarios for Adaptive Reward-guided Elicitation), a pipeline that composes benign scenarios from reusable scope and trap fragments, scores each run with a judge-free oracle flagging trap-pattern matches and unsolicited file additions or deletions, and uses Thompson sampling to steer each pair's run budget toward the scenarios that most often trigger it. Instantiating it over 24 overeager archetypes yields OverEager, which we run across a 4x5 matrix of four coding agents and five base models. Across 10,000 benign runs, 19.51% trigger overeager behavior, with per-pair rates spanning 11.9x. This variation is driven by the agent framework, not the model: the framework accounts for 56% of it against the model's 21%, so any single-framework or single-model evaluation undercounts the matrix by about a fifth.

LLMs for code generation are commonly evaluated in repeated-sampling settings using Pass@k, where multiple candidate programs are executed against unit tests under a finite sampling budget. While recent verifier-based reinforcement learning (RLVR) methods improve executable correctness, how these objectives affect redundancy among sampled programs remains poorly understood. In this work, we study implementation-level redundancy in code generation using JPlag, a plagiarism-detection system for code. Across models and benchmarks, we show that correctness-only RLVR often concentrates generations around repeated implementations, whereas Pass@k-aware objectives maintain lower redundancy and improve larger-budget performance. Motivated by these observations, we augment RLVR with direct anti-redundancy rewards based on JPlag similarity. Across 3 models and 3 benchmarks, discouraging near-duplicate generations reliably improves finite-budget executable performance, often matching or outperforming specialized Pass@k-aware objectives.

Evaluating the efficiency of algorithmic code requires test cases that expose runtime bottlenecks. Previous methods generate efficiency test cases either by increasing input size or by generating code-specific inputs that make the given implementation run slowly. Consequently, they do not address the structural input conditions that drive the algorithmic worst case. We introduce STAB, a specification-driven pipeline that generates test cases that expose algorithmic bottlenecks from a natural-language problem specification alone. STAB separates the task into constraint-bound maximization and adversarial structure injection. (i) The constraint saturator extracts constraints and resolves large admissible size assignments using rule-based saturation and CP-SAT optimization over related variables. (ii) The adversarial scenario injector retrieves implementation-level adversarial construction principles from a curated scenario catalog using keyword matching and K-nearest neighbors (KNN). STAB encodes the problem specification, resolved boundary, and retrieved construction principles into a structured generation specification, from which the LLM synthesizes a Python test case generator. On CodeContests, STAB raises the rate of generated test cases that expose algorithmic bottlenecks from 50.43% to 73.45% on average across open-source LLMs and from 57.45% to 71.85% on average across closed-source LLMs, with consistent gains across Python, Java, and C++. Our code is available at https://github.com/suhanmen/STAB.

Despite rapid progress in LLM-based code generation, existing models are predominantly trained on imperative languages, leaving functional programming languages (FPLs) such as Haskell, OCaml, and Scala chronically underexplored, with even frontier models performing substantially worse on FPLs. Fine-tuning is a natural remedy, but our experiments show that per-language fine-tuning fails to capture shared functional abstractions, while merged multi-language fine-tuning introduces cross-language interference. To address this, we introduce FPMoE, a lightweight, open-source code generation model built on a sparse Mixture-of-Experts (MoE) architecture with three language-specific routed experts (one each for Haskell, OCaml, and Scala) and a shared expert that captures cross-language functional patterns such as monadic reasoning and type-directed programming. This design resolves both failure modes simultaneously: dedicated experts eliminate interference, while the shared expert preserves abstractions that per-language models miss. On FPEval, FPMoE substantially outperforms fine-tuned baselines and, with only 3B active parameters, matches the performance of much larger models including DeepSeek-Coder-6.7B, Qwen2.5-Coder-14B-Instruct, and Qwen3-Coder-30B-A3B.

Code Large Language Models (CLLMs) serve as the core of modern code agents, enabling developers to automate complex software development tasks. In this paper, we present Poison-with-Style (PwS), a practical and stealthy model poisoning attack targeting CLLMs. Unlike prior attacks that assume an active adversary capable of directly embedding explicit triggers (e.g., specific words) into developers' prompts during inference, PwS leverages developers' code styles as covert triggers implicitly embedded within their prompts. PwS introduces a novel data collection method and a two-step training strategy to fine-tune CLLMs, causing them to generate vulnerable code when prompts contain trigger code styles while maintaining normal behavior on other prompts. Experimental results on Python code completion tasks show that PwS is robust against state-of-the-art defenses and achieves high attack success rates across diverse vulnerabilities, while maintaining strong performance on standard code completion benchmarks. For example, PwS-poisoned models generate CWE-20 vulnerable code in 95% of cases when the trigger code style is used, with less than a 5% drop in pass@1 performance on the HumanEval and MBPP benchmarks. Our implementation and dataset are here: https://github.com/khangtran2020/pws.

Specification synthesis, the task of automatically inferring formal specifications from program implementations and natural language, is important for refactoring, transpilation, optimization, and verification, yet remains an open challenge for large C++ repositories. Existing LLM-based approaches fail to simultaneously scale to such repositories, produce specifications expressive enough to capture systems-code features such as dynamic memory and heap-allocated data structures, and systematically validate those specifications to rule out incorrect candidates. We present Spec-Agent, an agentic system for synthesizing expressive, well-validated specifications across large C++ codebases. Spec-Agent targets a ladder of specification languages: propositional logic, first-order logic, propositional separation logic, and first-order separation logic. For each function, Spec-Agent uses static analysis and runtime heap tracing to select the appropriate target specification language, generalizes existing functional tests into fuzz harnesses, and iteratively refines LLM-generated candidates via counterexample-guided feedback. We evaluate Spec-Agent on open source C++ codebases comprising millions of lines of code. Spec-Agent synthesizes valid specifications for 85% of target functions, with no false positives observed under fuzzing and expert validation, outperforming Claude Code Opus 4.6 at 10x lower token cost.

Information localization within massive repositories is a cornerstone of agentic LLM systems. While synthetic data-driven optimization has proven successful in training LLMs, little attention has been paid to optimizing the agent's working environment (the repository itself) in a data-driven manner. To bridge this gap, we present Libra, a self-evolving framework that introduces mutable "catalogs" (hierarchical Markdown files serving as navigable indices) into the repository. Libra runs an LLM-driven optimization loop where a Prompter generates synthetic queries, a frozen Solver attempts to resolve them by navigating the catalogs, and a Healer rewrites the catalogs in response to the Solver's localization failures. Evaluations across 12 SWE-bench Lite repositories demonstrate that this environmental healing yields continual, logarithmic improvements in code localization accuracy. Furthermore, these environmental improvements transfer zero-shot across different LLMs and problem sets. Although the focus of this paper is to study the general behavior of such a system, we also demonstrate that a minimalist coding agent equipped with Libra-optimized catalogs outperforms state-of-the-art baselines. Code is available at https://github.com/salesforce-misc/Libra and data at https://huggingface.co/datasets/Salesforce/Libra.