AI Software Engineering

Traditional approaches to test case generation often involve manual effort and incur significant computational overhead. Additionally, these approaches are not scalable, and hence, unsuitable for complex software systems. Recently, Large Language Models (LLMs) have been applied to software testing. However, single-shot prompt engineering-based approaches tend to hallucinate and generate redundant test cases, resulting in fewer branches. To handle the above-mentioned limitations, in this paper, we propose FeedbackLLM, a novel automated language-agnostic test case generation framework based on tightly coupled two-stage approach. In the first stage, FeedbackLLM extracts the input constraints by parsing source code and generates the possible test cases. The quality of the test cases is evaluated in the second stage by the following two specialized LLM feedback agents: (i) Line Feedback Agent: extracts the metadata related to missed line executions and (ii) Branch Feedback Agent: extracts the metadata of the unexecuted branch conditions. The above agents operate in a two-stage process, communicating in tandem, and this procedure is repeated for k-steps. Further, we also introduced a redundancy prevention cache to avoid duplicate API requests and avoid unnecessary execution cycles. The performance of the proposed architecture is evaluated on the standard benchmark programs related to C and Python programs. FeedbackLLM demonstrated more line and branch coverage than baseline tools while scaling linearly in execution time.

Since 2022, AI-powered coding assistants have produced contradictory evidence: controlled studies report 20-56% productivity gains on well-scoped tasks, while the most rigorous RCT documents a 19% slowdown for experienced developers, and telemetry across 10,000+ developers shows 98% more pull requests but 91% longer review times with flat delivery metrics. This paper argues these findings constitute the Productivity-Reliability Paradox (PRP): a systematic phenomenon emerging from non-deterministic code generators and insufficient specification discipline. Through a multivocal literature review of 67 sources (2022-2026), this paper: (1) formally defines the PRP with three moderating variables (task abstraction, codebase maturity, developer experience) and two amplifying mechanisms (code review bottleneck, context window constraint); (2) proposes the AI-Augmented Methodology Taxonomy (AAMT), classifying six methodologies under three AI integration tiers; (3) introduces the Specification Governance Model (SGM), grounded in Transaction Cost Economics, with a practical governance decision guide; and (4) evaluates Spec Kit and TDAD as SGM instantiations via a four-month pilot study. Specification discipline, not model capability, is the binding constraint on AI-assisted software dependability.

Understanding how developers interact with AI coding assistants requires more than chat logs or git histories in isolation; it requires reconstructing the full context: which prompt led to which edit, what the developer tried and discarded, and how their strategy evolved over time. We present RECAP (Replay and Examine Captured AI Programming), an open-source platform that (1) passively records AI chat sessions and fine-grained code edits inside VS Code without disrupting the developer's workflow, (2) merges them into a unified timeline for interactive session replay, and (3) exposes an extensible analysis layer, with example modules for behavioral classification and AI reliance measurement. Deployed in a university software engineering course, RECAP captured 2,034 prompts and 8,239 code edits from 41 students across a multi-week project. We demonstrate how the platform's linked data and replay capabilities enable analyses of developer-AI interaction patterns that no single data source could support.

Hallucinations remain an unsolved problem for LLMs, and package hallucinations are a particularly dangerous instance of this phenomenon. Package hallucinations occur during code generation when a model fabricates non-existent software packages, recommending imports and installation commands for fictional libraries. This creates a critical supply-chain vulnerability; an attacker can proactively register such packages on public registries with malicious payloads that are subsequently installed and executed by developers or autonomous agents. These hallucinations enable a class of package confusion attack known as slopsquatting. To address this issue, we present Adaptive Unlearning (AU), a post-deployment framework that surgically suppresses package hallucinations while preserving general model utility. AU introduces a hybrid token-level objective that simultaneously reinforces valid outputs and suppresses hallucinated ones. Combined with an adaptive discovery loop that continuously surfaces new hallucination-inducing contexts without human supervision, AU enables generalization to unseen prompts and hallucinations. We demonstrate that AU reduces package hallucination rates by 88%, while maintaining performance on standard coding benchmarks. Our analysis shows that distributional changes are concentrated on package-related generations, leaving general coding behavior largely unaffected and confirming that AU's effect is isolated to the targeted distribution. AU relies entirely on model-generated data and requires no human annotation, representing a post-deployment hallucination mitigation framework.

Large language models are increasingly deployed as autonomous coding agents and have achieved remarkably strong performance on software engineering benchmarks. However, it is unclear whether such success transfers to computational scientific workflows, where tasks require not only strong coding ability, but also the ability to navigate complex, domain-specific procedures and to interpret results in the context of scientific claims. To address this question, we present AutoMat, a benchmark for evaluating LLM-based agents' ability to reproduce claims from computational materials science. AutoMat poses three interrelated challenges: recovering underspecified computational procedures, navigating specialized toolchains, and determining whether the resulting evidence supports a claim. By working closely with subject matter experts, we curate a set of claims from real materials science papers to test whether coding agents can recover and execute the end-to-end workflow needed to support (or undermine) such claims. We then evaluate multiple representative coding agent settings across several foundation models. Our results show that current LLM-based agents obtain low overall success rates on AutoMat, with the best-performing setting achieving a success rate of only 53%. Error analysis further reveals that agents perform worst when workflows must be reconstructed from paper text alone and that they fail primarily due to incomplete procedures, methodological deviations, and execution fragility. Taken together, these findings position AutoMat as both a benchmark for computational scientific reproducibility and a tool for diagnosing the current limitations of agentic systems in AI-for-science settings.

Generating diverse, readable statistical charts from tabular data remains challenging for LLMs, as many failures become apparent after rendering and are not detectable from data or code alone. Existing chart datasets also rarely provide fully aligned artifacts, such as executable code, dataset context, and question-answer pairs. We present a structured LLM-based workflow that decomposes chart generation into dataset screening, plot proposal, code synthesis, rendering, validation-driven refinement, description generation, and question-answer generation. By incorporating rendered-output validation, the workflow addresses visualization-specific failure modes such as readability and semantic mismatch. It treats chart generation as an inspectable process rather than a one-shot prompt-to-code task, retaining each chart with its code, dataset context, description, and question-answer pairs. Applied to UCI datasets, the workflow produces 1,500 charts from 74 datasets, spanning 24 chart families and paired with 30,003 question-answer pairs. We evaluate 16 multimodal LLMs (MLLMs) on these chart-question pairs. The results show that chart-syntax questions are nearly saturated, while value extraction, comparison, and reasoning remain more challenging, illustrating the workflow's utility for diagnostic studies of chart-grounded multimodal reasoning.

Automatic generation of executable Blender code from natural language remains challenging, with state-of-the-art LLMs producing frequent syntactic errors and geometrically inconsistent objects. We present BlenderRAG, a retrieval-augmented generation system that operates on a curated multimodal dataset of 500 expert-validated examples (text, code, image) across 50 object categories. By retrieving semantically similar examples during generation, BlenderRAG improves compilation success rates from 40.8% to 70.0% and semantic normalized alignment from 0.41 to 0.77 (CLIP similarity) across four state-of-the-art LLMs, without requiring fine-tuning or specialized hardware, making it immediately accessible for deployment. The dataset and code will be available at https://github.com/MaxRondelli/BlenderRAG.

Reinforcement learning (RL) from unit-test feedback has become a standard post-training recipe for improving large language models (LLMs) on code generation. However, the pass-all-tests binary reward can be sparse, yielding no learning signal on challenging problems where none of the sampled solutions passes all tests. A common remedy is to use the test-case pass rate as a surrogate reward. In this work, we study pass-rate rewards in critic-free RL for code generation (e.g., GRPO and RLOO) and report a consistent pattern across base models and algorithms: despite alleviating reward sparsity, pass-rate rewards do not reliably improve final performance over binary rewards in rigorous controlled experiments. To understand this discrepancy, we analyze reward density and the resulting gradient directions. We find that pass-rate rewards are denser, but the induced gradient updates do not consistently move probability mass toward full-pass solutions. This arises because test-case pass rate is a miscalibrated surrogate for progress toward full correctness, and partial-pass solutions within the same group can induce conflicting gradient directions that cancel out. Overall, our results suggest that, in critic-free RL, pass-rate rewards are insufficient to improve code generation and motivate reward designs that better align optimization with the goal of full correctness.

Developing effective test cases capable of thoroughly exercising large-scale software systems is inherently difficult, especially if such systems have voluminous, complex, and deeply nested source codes. In this work, we present a novel approach for generating test cases using a reinforcement learning-driven agentic framework where Proximal Policy Optimization (PPO) is coupled with an LLM engine to guide prompt selection during test generation. Our approach consists of two phases. In Phase I, the ToT-guided optimization agent partitions and minimizes the source code by removing redundancies without changing the functional behavior of the source code. In Phase II, a PPO-based policy network is trained to solve the problem of selecting prompts among eight different prompting techniques, such as Boundary Value Analysis, Random Fuzzing, etc., based on the inputted 11-dimensional state vector representing the source code complexity metrics and live coverage metrics to direct the LLM engine towards exploring unvisited paths in the program. The PPO agent receives rewards based on a combination of increases in line and branch coverages, penalties for unexplored branches, and rewards for reducing source code length. From experiments conducted on twenty benchmark programs, it is evident that the proposed approach, PPO-LLM, outperforms CBMC, kS-LLM, and kS-LLM++ in terms of branch and line coverage in almost all cases, for various loop bound values ranging from BOUND1 to BOUND2000. While at BOUND~1, the coverage of branches is 100% using PPO-LLM on the PALS suite, in comparison, it is around 86.8% using kS-LLM++. This confirms that adaptive prompt selection driven by PPO substantially outperforms static prompting strategies on PALS type programs.

Code generation, which aims to automatically generate source code from given programming requirements, has the potential to substantially improve software development efficiency. With the rapid advancement of large language models (LLMs), LLM-based code generation has attracted widespread attention from both academia and industry. However, as programming requirements become increasingly complex, existing LLMs still exhibit notable performance limitations. To address this challenge, recent studies have proposed training-based curriculum reinforcement learning (CRL) strategies to improve LLM code generation performance. Despite their effectiveness, existing CRL approaches suffer from several limitations, including misaligned requirement difficulty perception, the absence of requirement difficulty optimization, and suboptimal curriculum sampling strategies. In CRL-based code generation, programming requirements serve as the sole input to the model, making their quality and difficulty critical to training effectiveness. Motivated by insights from software requirements engineering, we propose RECRL, a novel requirement-aware curriculum reinforcement learning framework for enhancing LLM-based code generation. RECRL automatically perceives model-specific requirement difficulty, optimizes challenging requirements to improve training data utilization, and employs an adaptive curriculum sampling strategy to construct training batches with smoothly varying difficulty. Extensive experiments on five state-of-the-art LLMs across five widely-used code generation benchmarks by comparing with five state-of-the-art baselines, demonstrate the significant effectiveness of RECRL. For example, RECRL achieves an average Pass@1 improvement of 1.23%-5.62% over all state-of-the-art baselines.

Large Language Models (LLMs) are increasingly deployed to generate code for human-centered applications where demographic fairness is critical. However, existing evaluations focus almost exclusively on functional correctness, leaving social bias in LLM-generated code largely unexamined. Extending our prior work on Solar, we conduct a comprehensive empirical study using SocialBias-Bench, a benchmark of 343 real-world coding tasks spanning seven demographic dimensions. We evaluate four prominent LLMs and find severe bias across all models, with Code Bias Scores reaching up to 60.58%. We further show that standard prompt-level interventions, such as Chain-of-Thought reasoning and fairness persona assignment, inadvertently amplify bias rather than reduce it. We then investigate whether structured multi-agent software process frameworks can improve fairness, finding that structured pipelines reduce bias when early roles correctly scope what the code should and should not consider. However, adding explicit fairness instructions to all agent roles produces worse outcomes than providing none, suggesting that diffused responsibility goes unaddressed. To address these limitations, we propose the Fairness Monitor Agent (FMA), a modular component that plugs into any existing code generation pipeline without modifying it. FMA analyzes the task description to determine which attributes should be considered or restricted, then detects and corrects violations through an iterative review process, without requiring an executable test suite. Evaluated on all 343 tasks, FMA reduces bias by 65.1% compared to a developer agent alone and improves functional correctness from 75.80% to 83.97%, outperforming all other studied approaches.

This report documents the preparedness assessment of Code World Model (CWM), a model for code generation and reasoning about code from Meta. We conducted pre-release testing across domains identified in our Frontier AI Framework as potentially presenting catastrophic risks, and also evaluated the model's misaligned propensities. Our assessment found that CWM does not pose additional frontier risks beyond those present in the current AI ecosystem. We therefore release it as an open-weight model.

There has been intense debate among qualitative researchers about whether generative AI is suitable for qualitative research. In this paper, we summarize the broader ongoing discussion of generative AI in qualitative research and its implications for software engineering researchers. The qualitative research approach, small-q (positivist or post-positivist) or Big Q (non-positivist), is among the major criteria for determining whether generative AI can be used in qualitative research. In addition to research philosophy and research approach, skills, ethics, and personal preferences also play a role in researchers' decisions about whether to use AI in qualitative research.

Multimodal large language models (MLLMs) are increasingly used to translate visual artifacts into code, from UI mockups into HTML to scientific plots into Python scripts. A circuit diagram can be viewed as a visual domain-specific language for hardware: it encodes timing, topology, and bit level semantics that are invisible to casual inspection yet safety critical once fabricated in silicon. Translating such diagrams into register-transfer-level(RTL) code therefore represents an extreme reliability test for vision-to-code generation. We reveal a phenomenon we call Mirage: replacing a circuit diagram with a blank image leaves Pass@k unchanged or even higher, because models bypass the visual input and instead exploit identifier semantics in the module header to retrieve canonical RTL templates. This constitutes a new, highly covert class of defect in AI-assisted code generation that directly undermines MLLMs' trustworthiness. To quantify the effect, we construct C2VEVAL and evaluate eight MLLMs under a paired Normal/Anony protocol in which Anony mode anonymizes all identifiers in both the diagram and the module header; Anony-mode scores drop sharply across all models, confirming that high Normal-mode accuracy is largely a Mirage. We then propose VeriGround (4B), trained with identifier anonymization, refusal augmentation, and D-ORPO (Decision-Focused ORPO) preference alignment that up-weights pivotal generate-or-refuse tokens. VeriGround achieves Functional Pass@1 of 46.11%/42.51%(Normal/Anony) with a False Refusal Rate of only 1.20%/0.00%, while maintaining >92% Refusal Rate on blank images. With only 4B parameters, VeriGround performs on par with GPT-5.4 under Normal and significantly outperforms all baselines under Anony, confirming genuine visual grounding.

Understanding how Large Language Models (LLMs) make token-level decisions during code generation remains a major challenge for both researchers and practitioners. While recent tools provide insights into model internals or generation outcomes, they often lack decoding-time signals, fine-grained uncertainty measures, and interactive mechanisms for exploring alternative generation paths. We present TokenScope, an interactive interpretability and analysis tool for decoder-based LLMs that exposes token-level metrics, attention patterns, and structural information during generation. TokenScope supports interactive token replacement, counterfactual branching, and code-aware aggregation via abstract syntax trees. By unifying decoding-time signals with structural program analysis, TokenScope enables systematic investigation of LLM behaviour during code generation.

Integrated Circuit (IC) verification consumes nearly 70% of the IC development cycle, and recent research leverages Large Language Models (LLMs) to automatically generate testbenches and reduce verification overhead. However, LLMs have difficulty generating testbenches correctly. Unlike high-level programming languages, Hardware Description Languages (HDLs) are extremely rare in LLMs training data, leading LLMs to produce incorrect code. To overcome challenges when using LLMs to generate Universal Verification Methodology (UVM) testbenches and sequences, wepropose HAVEN (Hybrid Automated Verification ENgine) to prevent LLMs from writing HDL directly. For UVM testbench generation, HAVEN utilizes LLM agents to analyze design specifications to produce a structured architectural plan. The HAVEN Template Engine then combines with predefined and protocol-specific templates to generate all UVM components with correct bus-handshake timing. For UVM sequence generation, HAVEN introduces a Protocol-Aware Sequence Domain-Specific Language (DSL) that decomposes sequences into fine-grained step types. A set of predefined DSL patterns first establishes sequences that achieve a high coverage rate without LLM involvement. HAVEN continues to improve the coverage rate by iteratively leveraging LLM agents to analyze coverage gap reports and compose additional targeted DSL sequences. Unlike previous works, HAVEN is the first system that utilizes pre-defined, protocol-specific Jinja2 templates to generate all UVM components and UVM sequences using our proposed Protocol-Aware DSL and rule-based code generator. Our experimental results on 19 open-source IP designs spanning three interface protocols (Direct, Wishbone, AXI4-Lite) show that HAVEN achieves 100% compilation success, 90.6% code coverage, and 87.9% functional coverage on average, and is SOTA among LLM-assisted testbench generation systems.

Large Language Models (LLMs) are increasingly used for code editing, yet the prevalent full-code generation paradigm suffers from severe efficiency bottlenecks, posing challenges for interactive coding assistants that demand low latency and cost. Despite the predominant focus on scaling model capabilities, the edit format itself has been largely overlooked in model training. In this paper, we begin with a systematic study of conventional diff formats and reveal that fragile offsets and fragmented hunks make generation highly unnatural for LLMs. To address it, we introduce BlockDiff and FuncDiff, two structure-aware diff formats that represent changes as block-level rewrites of syntactically coherent units such as control structures and functions. Furthermore, we propose AdaEdit, a general adaptive edit strategy that trains LLMs to dynamically choose the most token-efficient format between a given diff format and full code. Extensive experiments demonstrate that AdaEdit paired with structure-aware diff formats consistently matches the accuracy of full-code generation, while reducing both latency and cost by over 30% on long-code editing tasks.

Large language model (LLM)-based coding agents increasingly rely on external memory to reuse prior debugging experience, repair traces, and repository-local operational knowledge. However, retrieved memory is useful only when the current failure is genuinely compatible with a previous one; superficial similarity in stack traces, terminal errors, paths, or configuration symptoms can lead to unsafe memory injection. This paper reframes issue-memory use as a selective, risk-sensitive control problem rather than a pure top-k retrieval problem. We introduce RSCB-MC, a risk-sensitive contextual bandit memory controller that decides whether an agent should use no memory, inject the top resolution, summarize multiple candidates, perform high-precision or high-recall retrieval, abstain, or ask for feedback. The system stores reusable issue knowledge through a pattern-variant-episode schema and converts retrieval evidence into a fixed 16-feature contextual state capturing relevance, uncertainty, structural compatibility, feedback history, false-positive risk, latency, and token cost. Its reward design penalizes false-positive memory injection more strongly than missed reuse, making non-injection and abstention first-class safety actions. In deterministic smoke-scale artifacts, RSCB-MC obtains the strongest non-oracle offline replay success rate, 62.5%, while maintaining a 0.0% false-positive rate. In a bounded 200-case hot-path validation, it reaches 60.5% proxy success with 0.0% false positives and a 331.466 microseconds p95 decision latency. The results show that, for coding-agent memory, the key question is not only which memory is most similar, but whether any retrieved memory is safe enough to influence the debugging trajectory.

LLMs have achieved strong results on both function-level code synthesis and repository-level code modification, yet a capability that falls between these two extremes -- compositional code creation, i.e., building a complete, internally structured class from a specification -- remains underserved. Current evaluations are either confined to isolated functions or rely on manually curated class-level tasks that are expensive to scale and increasingly susceptible to data contamination. We introduce ClassEval-Pro, a benchmark of 300 class-level tasks spanning 11 domains, constructed through an automated three-stage pipeline that combines complexity enhancement, cross-domain class composition, and integration of real-world GitHub code contributed after January 2025. Every task is validated by an LLM Judge Ensemble and must pass test suites with over 90% line coverage. We evaluate five frontier LLMs under five generation strategies. The best model achieves only 45.6% class-level Pass@1, with a 17.7-point gap between the strongest and weakest models, confirming the benchmark's discriminative power. Strategy choice strongly interacts with model capability: structured approaches such as bottom-up improve weaker models by up to 9.4 percentage points, while compositional generation collapses to as low as 1.3%. Error analysis over 500 manually annotated failures reveals that logic errors (56.2%) and dependency errors (38.0%) dominate, identifying cross-method coordination as the core bottleneck.

Large language model agents have made strong progress on software engineering, yet current systems suffer from a context coupling problem: the standard code editing interface conflates code inspection, modification planning, and edit execution within a single context window, forcing agents to interleave exploratory viewing with strictly formatted edit generation. Irrelevant context accumulates and edit reliability degrades. We propose SWE-Edit, which decomposes the editing interface into two specialized subagents: a Viewer that extracts task-relevant code on demand, and an Editor that executes modifications from high-level natural language plans -- letting the main agent focus on reasoning while delegating context-intensive operations to clean context windows. On SWE-Bench Verified, this decomposition raises resolve rate by 2.1 pp and cuts inference cost by 17.9%, with consistent gains across multiple reasoning-model families (Kimi-K2, MiniMax-M2.1, GLM-4.7). We further show that effective edit-format selection can be trained into a small model rather than requiring frontier-scale capacity: GRPO training on Qwen3-8B with an adaptive find-replace/whole-file-rewrite policy improves edit success by 12.5 pp and brings an 8B open-source editor to parity with GPT-5-nano on downstream SWE-Bench resolve rate. To enable rapid editor iteration, we release PR-Edit, a lightweight evaluation whose scores correlate strongly with SWE-Bench resolve rate. We release our code at https://github.com/microsoft/SWE-Edit.

SFT-then-RLVR is widely used for post-training reasoning models, but why this specific ordering, and why RLVR-only stalls at cold start, have lacked a unifying theoretical account. We provide that account under a unified loss family $J_Q$ using the Tsallis $q$-logarithm. $J_Q$ is a single-parameter family that interpolates between RLVR (at $q{=}0$, the \textit{exploitation pole}) and the log-marginal-likelihood over latent trajectories (at $q{=}1$, the \textit{density-estimation pole}), under which the standard pipeline corresponds to a stepwise $q{=}1 \to 0$ schedule. All members share the same per-example gradient direction, differing only by a per-instance amplification $P_θ^{-q}$ that reweights each instance independently of the learning rate. Under gradient flow analysis, we show that the exploitation pole requires $Ω(\frac{1}{p_0})$ time to escape cold start but is robust to label noise, while the density-estimation pole escapes in $Θ\big(\log(\frac{1}{p_0})\big)$ but memorizes label noise. This separation explains how SFT ($q{=}1$) first moves the model out of the cold-start regime, followed by the more robust RLVR ($q{=}0$), under the SFT-then-RLVR paradigm. We further derive two Monte Carlo estimators that directly optimize fixed-$q$ on the $J_Q$ continuum, without annotated rationales: Gradient-Amplified RL (GARL) and Posterior-Attenuated Fine-Tuning (PAFT), with shared bias $O\big(\frac{q}{M P_θ^q}\big)$ but different variance and stability properties. On FinQA, HotPotQA, and MuSiQue, GARL at sufficiently high $q$ substantially mitigates cold-start stalling, escaping cold start where GRPO fails entirely. In warm start, GARL at low $q$ dominates FinQA where training is stable; on HotPotQA and MuSiQue, GARL destabilizes and PAFT at $q{=}0.75$ remains stable, reaching $47.9$ \texttt{m@16} on HotPotQA ($+13.9$ over GRPO).

Existing REST API testing tools are typically evaluated using code coverage and crash-based fault metrics. However, recent LLM-based approaches increasingly generate tests from NL requirements to validate functional behaviour, making traditional metrics weak proxies for whether generated tests validate intended behaviour. To address this gap, we present RESTestBench, a benchmark comprising three REST services paired with manually verified NL requirements in both precise and vague variants, enabling controlled and reproducible evaluation of requirement-based test generation. RESTestBench further introduces a requirements-based mutation testing metric that measures the fault-detection effectiveness of a generated test case with respect to a specific requirement, extending the property-based approach of Bartocci et al. . Using RESTestBench, we evaluate two approaches across multiple state-of-the-art LLMs: (i) non-refinement-based generation, and (ii) refinement-based generation guided by interaction with the running SUT. In the refinement experiments, RESTestBench assesses how exposure to the actual implementation, valid or mutated, affects test effectiveness. Our results show that test effectiveness drops considerably when the generator interacts with faulty or mutated code, especially for vague requirements, sometimes negating the benefit of refinement and indicating that incorporating actual SUT behaviour is unnecessary when requirement detail is high.

Harnesses are now central to coding-agent performance, mediating how models interact with tools and execution environments. Yet harness engineering remains a manual craft, because automating it faces a heterogeneous action space across editable components, voluminous trajectories that bury actionable signal, and edits whose effect is hard to attribute. We introduce Agentic Harness Engineering (AHE), a closed loop that addresses these challenges through three matched observability pillars: (1) component observability gives every editable harness component a file-level representation so the action space is explicit and revertible; (2) experience observability distills millions of raw trajectory tokens into a layered, drill-down evidence corpus that an evolving agent can actually consume; and (3) decision observability pairs every edit with a self-declared prediction, later verified against the next round's task-level outcomes. Together, these pillars turn every edit into a falsifiable contract, so harness evolution proceeds autonomously without collapsing into trial-and-error. Empirically, ten AHE iterations lift pass@1 on Terminal-Bench 2 from 69.7% to 77.0%, surpassing the human-designed harness Codex-CLI (71.9%) and the self-evolving baselines ACE and TF-GRPO. The frozen harness transfers without re-evolution: on SWE-bench-verified it tops aggregate success at 12% fewer tokens than the seed, and on Terminal-Bench 2 it yields +5.1 to +10.1pp cross-family gains across three alternate model families, indicating the evolved components encode general engineering experience rather than benchmark-specific tuning. Ablations localize the gain to tools, middleware, and long-term memory rather than the system prompt, suggesting factual harness structure transfers while prose-level strategy does not.

Source Code Plagiarism Detection (SCPD) plays an important role in maintaining fairness and academic integrity in software engineering education. Code Evaluation Metrics (CEMs) are developed for assessing code generation tasks. However, it remains unclear whether such metrics can reliably detect plagiarism across different levels of modification (L1-L6), increasing in complexity. In this paper, we perform a comparative empirical study using two open-source labelled datasets, ConPlag (raw and template-free versions) and IRPlag. We evaluate five CEMs, namely CodeBLEU, CrystalBLEU, RUBY, Tree Structured Edit Distance (TSED), and CodeBERTScore. The performance is evaluated using threshold-free ranking-based measures to assess overall, per dataset, and per-level plagiarism performance. The results are compared against state-of-the-art (SOTA) Source Code Plagiarism Detection Tools (SCPDTs), JPlag and Dolos. Our findings show that without preprocessing, Dolos achieves the highest overall ranking performance, while among the individual metrics, CrystalBLEU, CodeBLEU, and RUBY outperform JPlag. Performance is strongest at L1 and drops from L4 onward, while CrystalBLEU remains competitive on L6. With preprocessing, CrystalBLEU surpasses Dolos overall. Per dataset, Dolos achieved the best ranking on the ConPlag raw dataset, while CrystalBLEU was the best-performing metric on the remaining datasets. At the plagiarism levels, Dolos remains strongest on L4, while Crystal-BLEU leads most of the remaining difficult levels. These results indicate that CEMs are comparable to dedicated tools in terms of ranking metrics.

Source code and its accompanying comments are complementary yet naturally aligned modalities-code encodes structural logic while comments capture developer intent. However, existing vulnerability detection methods mostly rely on single-modality code representations, overlooking the complementary semantic information embedded in comments and thus limiting their generalization across complex code structures and logical relationships. To address this, we propose MultiVul, a multimodal contrastive framework that aligns code and comment representations through dual similarity learning and consistency regularization, augmented with diverse code-text pairs to improve robustness. Experiments on widely adopted DiverseVul and Devign datasets across four large language models (LLMs) (i.e., DeepSeek-Coder-6.7B, Qwen2.5-Coder-7B, StarCoder2-7B, and CodeLlama-7B) show that MultiVul achieves up to 27.07% F1 improvement over prompting-based methods and 13.37% over code-only Fine-Tuning, while maintaining comparable inference efficiency.

AI coding agents powered by large language models can read codebases and produce functional code, but they routinely violate team-specific product decisions that are invisible in the source code alone. We introduce a controlled benchmark measuring decision compliance, the rate at which an AI coding agent follows established product, design, and engineering decisions, across 8 realistic software engineering tasks containing 41 weighted decision points. We compare a baseline configuration (Claude Code with codebase access only) against an augmented configuration that adds Brief, a product-context retrieval system providing spec generation, mid-build consultation, and retrieval of recorded decisions, persona pain points, customer signals, and competitive intelligence. On identical prompts and the same repository, the augmented configuration achieves 95% decision compliance versus 46% for the baseline, a 49 percentage point improvement. Per-decision analysis reveals that the baseline achieves 100% compliance on decisions visible in the codebase and 0-33% on decisions requiring product context, suggesting that product-context retrieval is a key driver of the improvement. We release the benchmark repository, all 16 pull requests, and scoring harness for independent reproduction.

Adaptive programming practice often relies on fixed libraries of worked examples and practice problems, which require substantial authoring effort and may not correspond well to the logical errors and partial solutions students produce while writing code. As a result, students may receive learning content that does not directly address the concepts they are working to understand, while instructors must either invest additional effort in expanding content libraries or accept a coarse level of personalization. We present an approach for knowledge-component (KC) guided educational content generation using pattern-based KCs extracted from student code. Given a problem statement and student submissions, our pipeline extracts recurring structural KC patterns from students' code through AST-based analysis and uses them to condition a generative model. In this study, we apply this approach to worked example generation, and compare baseline and KC-conditioned outputs through expert evaluation. Results suggest that KC-conditioned generation improves topical focus and relevance to students' underlying logical errors, providing evidence that KC-based steering of generative models can support personalized learning at scale.

Deep Learning methods are becoming prominent in automated software bug detection; however, they lack the global understanding of the given code. Consequently, their performance tends to degrade, especially when they are applied to large interconnected code bases or complex modular programs. Recently, Large Language Models (LLMs) have proven to be effective at capturing dependencies among multiple interconnected modules in the codebase. This motivated us to propose the Flow-Graph-Driven Multi-Agent Framework (FGDM), which is composed of four agents that operate in a sequential manner. The framework converts the received code to a flow graph, identifies the erroneous segments, and further generates the repaired code. All the employed agents utilize Chain-of-Thought (COT) and Tree-of-Thoughts (TOT) prompts. Additionally, we also integrated with the FAISS vector database to retrieve similar previous bugs and their repairs. We demonstrated the efficacy of the proposed framework over 100 programs from several projects, including Ansible, Black, FastAPI, Keras, Luigi, Matplotlib, Pandas, Scrapy, SpaCy, and Tornado in both C and Python programs. Our experiments demonstrate that the FGDM outperforms the extant approaches and yielded reductions with a mean of 24.33 and 8.37 in Levenshtein distance and similarities of 0.951 and 0.974 in cosine similarity for Python and C, respectively.

Large language models are widely used for code generation, yet they rely on an implicit assumption that the task descriptions are sufficiently detailed and well-formed. However, in practice, users may provide defective descriptions, which can have a strong effect on code correctness. To address this issue, we develop SpecValidator, a lightweight classifier based on a small model that has been parameter-efficiently finetuned, to automatically detect task description defects. We evaluate SpecValidator on three types of defects, Lexical Vagueness, Under-Specification and Syntax-Formatting on 3 benchmarks with task descriptions of varying structure and complexity. Our results show that SpecValidator achieves defect detection of F1 = 0.804 and MCC = 0.745, significantly outperforming GPT-5-mini (F1 = 0.469 and MCC = 0.281) and Claude Sonnet 4 (F1 = 0.518 and MCC = 0.359). Perhaps more importantly, our analysis indicates that SpecValidator can generalize to unseen issues and detect unknown Under-Specification defects in the original (real) descriptions of the benchmarks used. Our results also show that the robustness of LLMs in task description defects depends primarily on the type of defect and the characteristics of the task description, rather than the capacity of the model, with Under-Specification defects being the most severe. We further found that benchmarks with richer contextual grounding, such as LiveCodeBench, exhibit substantially greater resilience, highlighting the importance of structured task descriptions for reliable LLM-based code generation.

Large language models (LLMs) perform strongly on general-purpose code generation, yet their applicability to enterprise domain-specific languages (DSLs) remains underexplored, especially for repository-scale change generation spanning multiple files and folder structures from a single natural-language (NL) instruction. We report an industrial case study at BMW that adapts code-oriented LLMs to generate and modify project-root DSL artifacts for an Xtext-based DSL that drives downstream Java/TypeScript code generation. We develop an end-to-end pipeline for dataset construction, multi-file task representation, model adaptation, and evaluation. We encode DSL folder hierarchies as structured, path-preserving JSON, allowing single-response generation at repository scale and learning cross-file dependencies. We evaluate two instruction-tuned code LLMs (Qwen2.5-Coder and DeepSeek-Coder, 7B) under three configurations: baseline prompting, one-shot in-context learning, and parameter-efficient fine-tuning (QLoRA). Beyond standard similarity metrics, we introduce task-specific measures that assess edit correctness and repository structural fidelity. Fine-tuning yields the most significant gains across models and metrics, achieving high exact-match accuracy, substantial edit similarity, and structural fidelity of 1.00 on our held-out set for multi-file outputs. At the same time, one-shot in-context learning provides smaller but consistent improvements over baseline prompting. We further validate practical utility via an expert developer survey and an execution-based check using the existing code generator.

Chart-to-code generation converts a chart image into an executable plotting script, enabling faithful reproduction and editable visualizations. Existing methods are largely Python-centric, limiting practical use and overlooking a critical source of supervision: the same chart can be expressed by semantically equivalent scripts in different plotting languages. To fill this gap, we introduce Chart2NCode, a dataset of 176K charts paired with aligned scripts in Python, R, and LaTeX that render visually equivalent outputs, constructed via a metadata-to-template pipeline with rendering verification and human quality checks. Building on a LLaVA-style architecture, we further propose CharLuMA, a parameter-efficient adaptation module that augments the multimodal projector with a language-conditioned mixture of low-rank subspaces, allowing the model to share core chart understanding while specializing code generation to the target language through lightweight routing. Extensive experiments show consistent gains in executability and visual fidelity across all languages, outperforming strong open-source baselines and remaining competitive with proprietary systems. Further analyses reveal that balanced multi-language supervision benefits all languages and that the adapter allocates a compact shared core plus language-specific capacity. Codes and data are available at https://github.com/Zhihan72/CharLuMA.

Context: Software vulnerabilities pose significant security threats to software systems, especially as software is increasingly used across many areas of daily life, including health, government, and finance. Recently, transformer-based models have demonstrated promising results in automatic software vulnerability identification due to their robust contextual modelling and representation learning capabilities. Objectives: While numerous systematic literature reviews (SLRs) have examined machine learning and deep learning methods for identifying vulnerabilities, a more transformer-centric analysis remains to be explored. This SLR critically analysed 80 studies published between 2021 and 2025 that utilised transformer models to identify software vulnerabilities. Methods: Using Kitchenhams SLR guidelines, we methodically evaluate current research from various perspectives, encompassing study trends, datasets and sources, programming languages, transformer frameworks, detection detail levels, assessment metrics, reference models, types of vulnerabilities, and experimental configurations. Results: We classify transformer models into encoder, decoder, and combined architectures and analyse both pre-trained and fine-tuned versions utilized on source code, logs, and smart contracts. The results emphasise prevailing research trends, frequently utilised benchmarks, and main baselines. It also uncovers crucial technical issues like data imbalance, interpretability, scalability, and generalization across programming languages. Conclusion: By integrating current evidence and recognising unaddressed research areas, this SLR provides a consolidated resource for researchers and professionals seeking to develop more reliable, precise, and interpretable transformer-based vulnerability identification systems.

Automated code review (ACR) bots are increasingly used in industrial software development to assist developers during pull request (PR) review. As adoption grows, a key challenge is how to evaluate the usefulness of bot-generated comments reliably and at scale. In practice, such evaluation often relies on developer actions and annotations that are shaped by contextual and organizational factors, complicating their use as objective ground truth. We examine the feasibility and limitations of automating the evaluation of LLM-powered ACR bots in an industrial setting. We analyze an industrial dataset from Beko comprising 2,604 bot-generated PR comments, each labeled by software engineers as fixed/wontFix. Two automated evaluation approaches, G-Eval and an LLM-as-a-Judge pipeline, are applied using both binary decisions and a 0-4 Likert-scale formulation, enabling a controlled comparison against developer-provided labels. Across Gemini-2.5-pro, GPT-4.1-mini, and GPT-5.2, both evaluation strategies achieve only moderate alignment with human labels. Agreement ratios range from approximately 0.44 to 0.62, with noticeable variation across models and between binary and Likert-scale formulations, indicating sensitivity to both model choice and evaluation design. Our findings highlight practical limitations in fully automating the evaluation of ACR bot comments in industrial contexts. Developer actions such as resolving or ignoring comments reflect not only comment quality, but also contextual constraints, prioritization decisions, and workflow dynamics that are difficult to capture through static artifacts. Insights from a follow-up interview with a software engineering director further corroborate that developer labeling behavior is strongly influenced by workflow pressures and organizational constraints, reinforcing the challenges of treating such signals as objective ground truth.

Large Language Models (LLMs) have achieved strong performance on general code generation, but their effectiveness drops sharply in enterprise settings where software development relies on internal private libraries absent from public pre-training corpora. Existing Retrieval-Augmented Generation (RAG) methods provide a training-free solution by retrieving static API documentation, but our analysis shows that documentation mainly helps models identify what APIs to use and remains insufficient for teaching how to use them correctly. Even with oracle API-document retrieval, LLMs still make recurring errors at the API, cross-API, and task levels, including API misuse or hallucination, flawed API composition, and incorrect solution strategies. To address this limitation, we propose MEMCoder, a training-free self-evolving memory framework for private-library code generation. MEMCoder augments existing RAG pipelines with a Multi-level Evolving Memory that continuously accumulates and reuses execution-derived Usage Guidelines at the API, cross-API, and task levels. During generation, MEMCoder retrieves both static API documentation and relevant historical memories to guide code generation; after execution, it analyzes feedback to refine memory through a closed loop of generation, execution, reflection, and update. Extensive experiments on NdonnxEval and NumbaEval show that MEMCoder consistently enhances different RAG backbones across LLMs of different scales, yielding an average absolute pass@1 improvement of 18.41 percentage points. Moreover, MEMCoder outperforms existing self-evolving memory methods and validates the effectiveness of organizing execution feedback into multi-level usage memories.

Recent image generation and editing models demonstrate robust adherence to instructions and high visual quality on academic benchmarks. However, their performance on paid, real-world design projects remains uncertain. We introduce \textbf{ServImage}, a benchmark that explicitly correlates model outputs with economic value in commercial design projects. ServImage consists of (i) \textbf{\textit{ServImageBench}}: a dataset of 1.07k paid commercial design tasks and 2.05k designer deliverables totaling over $295k, covering portrait, product, and digital content, along with 33k candidate images and 33k human annotations. (ii) \textbf{\textit{ServImageScore}}: an integrated scoring system that combines three quality dimensions: baseline requirements fulfilment, visual execution quality, and commercial necessity satisfaction. These three dimensions are designed to characterize the factors that drive human payment decisions and indicate whether an image is commercially acceptable. (iii) \textbf{\textit{ServImageModel}}: under this scoring system, we propose a payment prediction model trained on the human-annotated candidate images, achieving 82.00% accuracy in predicting human payment decisions and producing calibrated payment probabilities. ServImage provides a comprehensive foundation for assessing the commercial viability of image generation models and offers a scalable resource for future research on economically grounded vision systems \href{https://github.com/FengxianJi/ServImage}{Github.}

Decompilation -- recovering source code from compiled binaries -- is essential for security analysis, malware reverse engineering, and legacy software maintenance. However, existing decompilers produce code that often fails to compile or execute correctly, limiting their practical utility. We present a multi-agent framework that transforms decompiled code into re-executable source through Multi-level Constraint-Guided Decompilation (MCGD). Our approach employs a hierarchical validation pipeline with three constraint levels: (1) syntactic correctness via parsing, (2) compilability via GCC, and (3) behavioral equivalence via LLM-generated test cases. When validation fails, specialized LLM agents iteratively refine the code using structured error feedback. We evaluate our framework on 1,641 real-world binaries from ExeBench across three decompilers (RetDec, Ghidra, and Angr). Our framework achieves 84-97% re-executability, improving baseline decompiler output by 28-89 percentage points. In comparison with state-of-the-art LLM-based decompilation methods using the same GPT-4o backbone, our approach (84.1%) outperforms LLM4Decompile (80.3%), SK2Decompile (73.9%), and SALT4Decompile (61.8%). Our ablation study reveals that execution-based validation is critical: compile-only approaches achieve 0% behavioral correctness despite 91-99% compilation rates. The system converges efficiently, with 90%+ binaries reaching correctness within 2 iterations at an average cost of $0.03-0.05 per binary. Our results demonstrate that constraint-guided agentic refinement can bridge the gap between raw decompiler output and practically useful source code.

Software documentation frequently becomes outdated or fails to exist entirely, yet developers need focused views of their codebase to understand complex systems. While automated reverse engineering tools can generate UML diagrams from code, they produce overwhelming detail without considering developer intent. We introduce query-driven UML diagram generation, where LLMs create diagrams that directly answer natural language questions about code. Unlike existing methods, our approach produces semantically focused diagrams containing only relevant elements with contextual descriptions. We fine-tune Qwen2.5-Coder-14B on a curated dataset of code files, developer queries, and corresponding diagram representations in a structured JSON format, evaluating with both automatic detection of structural defects and human assessment of semantic relevance. Results demonstrate that fine-tuning on a modest amount of manually corrected data yields dramatic improvements: our best model achieves the highest F1 scores while reducing defect rates below state-of-the-art LLMs, generating diagrams that are both structurally sound and semantically faithful to developer queries. Thus, we establish the feasibility of using LLMs for scalable contextual, on-demand documentation generation. We make our code and dataset publicly available at https://github.com/i-need-a-pencil/query2diagram.

Recent advances in large language models (LLMs) have shown promise in formal theorem proving, yet evaluating semantic correctness remains challenging. Existing evaluations rely on indirect proxies such as lexical overlap with human-annotated proof, or expensive manual inspection. Inspired by the shift from lexical comparison to test-based evaluation in code generation, we propose T , a framework that evaluates the semantic correctness of formal theorems: a generated theorem is considered correct only if all dependent successor theorems compile successfully, analogous to integration testing. We construct a benchmark from 5 real-world Lean 4 repositories, comprising 2,206 problems paired with 41 successor theorems on average, automatically extracted without human effort. Experiments demonstrate that while state-of-the-art models achieve high compilation success, they perform significantly worse under our semantic metric. The best model, Claude-Sonnet-4.5, achieves only 38.9% Testing Accuracy on the full set, given both natural language proof and successor theorems as context, revealing a critical gap in current theorem generation capabilities.

Reward hacking in code generation, where models exploit evaluation loopholes to obtain high reward without correctly solving the intended task, poses a critical challenge for Reinforcement Learning (RL) and the deployment of reasoning models. Existing studies often rely on explicitly prompted hacking trajectories, but it remains unclear whether monitors trained on such data can detect reward hacks that arise without direct hacking instructions during RL training. In this work, we introduce Trace-and-Amplify, a framework for scalable curation of reward-hacking trajectories that arise during RL training without explicit hacking instructions. The framework uses unit-test tracers to identify hacking solutions when they occur and retains such trajectories for monitor training and evaluation. Through controlled comparisons between monitors trained on prompt-elicited hacking trajectories and training-time reward-hacking trajectories collected by Trace-and-Amplify, we find that \textbf{(1) prompt-elicited-data-trained monitors often fail to generalize to trajectories curated by our framework}, and \textbf{(2) monitors trained on our Trace-and-Amplify trajectories demonstrate stronger generalizability to unseen hacking types}. Our results indicate that prompted reward hacking data may not fully reflect training-time reward-hacking behaviors, and that relying solely on these data can lead to misleading conclusions. Codebase is available at https://github.com/LichenLillc/CoTMonitoring.git

Large language models (LLMs) have demonstrated strong performance on a wide range of software engineering tasks, including code generation and analysis. However, most prior work relies on cloud-based models or specialized hardware, limiting practical applicability in privacy-sensitive or resource-constrained environments. In this paper, we present a systematic empirical evaluation of two locally deployed LLMs, LLaMA 3.2 and Mistral, for real-world Python bug detection using the BugsInPy benchmark. We evaluate 349 bugs across 17 projects using a zero-shot prompting approach at the function level and an automated keyword-based evaluation framework. Our results show that locally executed models achieve accuracy between 43% and 45%, while producing a large proportion of partially correct responses that identify problematic code regions without pinpointing the exact fix. Performance varies significantly across projects, highlighting the importance of codebase characteristics. The results demonstrate that local models can identify a meaningful share of bugs, though precise localization remains difficult for locally executed LLMs, particularly when handling complex and context dependent bugs in realistic development scenarios.

Software engineering (SE) organizations operate in a knowledge-intensive domain where critical assets -- architectural expertise, design rationale, and system intuition -- are overwhelmingly tacit and volatile. The departure of key contributors or the decay of undocumented decisions can severely impair project velocity and software quality. While conventional SE risk management optimized for schedule and budget is common, the intangible knowledge risks that determine project success remain under-represented. The goal of this research work is to propose and evaluate the Knowledge Lever Risk Management (KLRM) Framework, designed specifically for the software development lifecycle. The primary objectives are to: (1) recast intangible knowledge assets as active mechanisms for risk mitigation (Knowledge Levers); (2) integrate these levers into a structured four-phase architecture (Audit, Alignment, Activation, Assurance); and (3) provide a formal stochastic model to quantify the impact of lever activation on project knowledge capital. We detail the application of these levers through software-specific practices such as pair programming, architectural decision records (ADRs), and LLM-assisted development. Stochastic Monte Carlo simulations demonstrate that full lever activation increases expected knowledge capital by 63.8% and virtually eliminates knowledge crisis probability. Our research shows that knowledge lever activation improves alignment across the project management iron triangle (scope, time, cost) by reducing rework and rediscovery costs.

Research shows that dialogue, the interactive process through which participants articulate their thinking, plays a central role in constructing shared understanding, coordinating action, and shaping learning outcomes in teams. Analysing dialogue content has been central to advancing team learning theory and informing the design of computer-supported collaborative learning environments, yet this progress has depended on labour-intensive qualitative coding. LLMs offer new possibilities for automating and enhancing the dialogue layer within emerging multimodal learning analytics approaches, with recent studies showing that they can approximate human coding through few-shot prompting. However, prior work has focused on replicating human coding accuracy for research purposes, rather than addressing a more educationally consequential question: how can we design prompts that allow an LLM to label team dialogue accurately and fast enough to be useful in real settings, such as in-person healthcare simulations, where results must be returned quickly and computational cost and sustainability also matter? This paper investigates how prompt design and batching strategies can be optimised to balance coding accuracy, processing time, and environmental impact in team-based healthcare simulation debriefing. Using a dataset of 11,647 utterances coded across 6 dialogue constructs, we compared 4 prompt designs across varying batch sizes, evaluating coding performance, processing time, and energy consumption, as well as the trade-offs between these metrics. Results indicate that increasing batch size improves speed and reduces energy use, but negatively impacts coding performance. Beyond demonstrating the feasibility of LLM-based qualitative analysis, this study offers practical guidance for scaling dialogue analytics in contexts where timeliness, privacy, and sustainability are critical.

Code review is central to software engineering education but hard to scale in capstone projects due to tight deadlines, uneven peer feedback, and limited prior experience. We investigate an LLM-as-reviewer integrated directly into GitHub pull requests (human-in-the-loop) across two cohorts (more than 100 students, 2023--2024). Using a mixed-methods design -- GitHub data, reflective reports, and a targeted survey -- we examine engagement and responsiveness as behavioral indicators of self-regulated learning processes. Quantitatively, the 2024 cohort produced more iterative activity (1176 vs. 581 PRs), while technical issues observed in 2023 (227 failed AI attempts) dropped to zero after tool and instructional refinements. Despite different adoption levels (93% vs. 50% of teams using the tool), responsiveness was stable: 32% (2023) and 33% (2024) of successfully AI-reviewed PRs were followed by subsequent commits on the same PR. Qualitatively, students used the LLM's structured comments to focus reviews and discuss code quality, while guidance reduced over-reliance. We contribute: (i) an in-workflow design for an AI reviewer that scaffolds learning while mitigating cognitive offloading; (ii) a repeated cross sectional comparison across two cohorts in authentic settings; (iii) a mixed-methods analysis combining objective GitHub metrics with student self-reports; and (iv) evidence-based pedagogical recommendations for responsible, student-led AI-assisted review.

Automating repository-level software engineering tasks is a foundational challenge for autonomous code agents, largely due to the difficulty of configuring executable environments. However, manual configuration remains a labor-intensive bottleneck, necessitating a transition toward fully automated environment configuration. Existing approaches often rely on pre-defined artifacts or are restricted to specific programming languages, limiting their applicability to diverse real-world repositories. In this paper, we first propose RAT (RunAnyThing), a modular and extensible agent framework for fully automated configuration across programming languages on arbitrary repositories. RAT adopts a multi-stage pipeline that integrates language-aware abstraction, image initialization, specialized configuration toolset, and robust sandbox. Furthermore, to enable rigorous evaluation, we propose RATBench, a benchmark reflects the comprehensive coverage of real-world repositories. Extensive experiments demonstrate that RAT achieves state-of-the-art performance, improving Environment Setup Success Rate (ESSR) by an average of 36.1% over strong baselines.

Lean 4 autoformalization has become increasingly popular in recent years, with frontier language models and open-weight autoformalizers now producing valid formalizations of mathematical theorems. However, these evaluations often rely on single canonical phrasings of theorems and rarely probe whether outputs are robust to natural variation in inputs, while prior work has shown that semantically equivalent paraphrases often induce divergent formal outputs. We study the structure of these divergences in Lean 4 by applying deterministic paraphrase rules to datasets of undergraduate and Olympiad-level math problems. Across four frontier models and three open-weight autoformalizers, we find that paraphrase sensitivity is dominated by failures at the code-generation layer, and that these failures are typed differently by dataset. Furthermore, these patterns generalize to open-weight models, showing that state-of-the-art autoformalizers still struggle to generate valid Lean code. Our results provide a failure-mode taxonomy for autoformalization and motivate training-time interventions targeted at specific compilation failures.

Existing multi-agent Large Language Model (LLM) frameworks for code generation typically use execution feedback and improve iteratively using Input/Output (I/O) test cases. However, this does not work for scientific workflows, where I/O test cases do not exist, and generating them requires solving the very problem at hand. To address this, we introduce MOSAIC, a training-free multi-agent framework for scientific code generation without I/O supervision. Instead of execution feedback, MOSAIC employs a student-teacher knowledge distillation framework that grounds generation through domain-specific examples and structured problem decomposition. To further mitigate hallucinations across chained subproblems, we introduce a Consolidated Context Window (CCW) for maintaining consistent reasoning across agents. Experiments on the SciCode benchmark show that MOSAIC improves accuracy, executability, and numerical precision over existing approaches while relying on lightweight models.

We present Code Broker, a multi agent system built on Google s Agent Development Kit ADK that analyses Python source code from individual files, local directory trees, or remote GitHub repositories and generates structured, actionable quality assessment reports. The system realises a hierarchical five agent architecture in which a root orchestrator coordinates a sequential pipeline agent that, in turn, dispatches three specialised agents concurrently a Correctness Assessor, a Style Assessor, and a Description Generator before synthesising their findings through an Improvement Recommender. Reports quantify four quality dimensions correctness, security, style, and maintainability on a normalised scale and are rendered in both Markdown and HTML for integration into diverse developer workflows. Code Broker fuses LLM based semantic reasoning with deterministic static analysis signals from Pylint, employs asynchronous execution with exponential backoff retry logic to improve robustness under transient API failures, and explores lightweight session memory for retaining and querying prior assessment context across runs. We frame this paper as a technical report on system design, prompt engineering, and tool orchestration, and present a preliminary qualitative evaluation on representative Python codebases of varying scale. The results indicate that parallel specialised agents produce readable, developer oriented feedback that complements traditional linting, while also foregrounding current limitations in evaluation depth, security tooling, large repository handling, and the exclusive reliance on in memory persistence. All code and reproducibility materials are publicly available: https://github.com/Samir-atra/agents_intensive_dev.

Formalising informal mathematical reasoning into formally verifiable code is a significant challenge for large language models. In scientific fields such as physics, domain-specific machinery (\textit{e.g.} Dirac notation, vector calculus) imposes additional formalisation challenges that modern LLMs and agentic approaches have yet to tackle. To aid autoformalisation in scientific domains, we present FormalScience; a domain-agnostic human-in-the-loop agentic pipeline that enables a single domain expert (without deep formal language experience) to produce \textit{syntactically correct} and \textit{semantically aligned} formal proofs of informal reasoning for low economic cost. Applying FormalScience to physics, we construct FormalPhysics, a dataset of 200 university-level (LaTeX) physics problems and solutions (primarily quantum mechanics and electromagnetism), along with their Lean4 formal representations. Compared to existing formal math benchmarks, FormalPhysics achieves perfect formal validity and exhibits greater statement complexity. We evaluate open-source models and proprietary systems on a statement autoformalisation task on our dataset via zero-shot prompting, self-refinement with error feedback, and a novel multi-stage agentic approach, and explore autoformalisation limitations in modern LLM-based approaches. We provide the first systematic characterisation of semantic drift in physics autoformalisation in terms of concepts such as notational collapse and abstraction elevation which reveals what formal language verifies when full semantic preservation is unattainable. We release the codebase together with an interactive UI-based FormalScience system which facilitates autoformalisation and theorem proving in scientific domains beyond physics.https://github.com/jmeadows17/formal-science

Large Language Models (LLMs) show promise in automated software engineering, yet their guarantee of correctness is frequently undermined by erroneous or hallucinated code. To enforce model honesty, formal verification requires LLMs to synthesize implementation logic alongside formal specifications that are subsequently proven correct by a mathematical verifier. However, the transition from informal natural language to precise formal specification remains an arduous task. Our work addresses this by providing the NaturalLanguage2VerifiedCode (NL2VC)-60 dataset: a collection of 60 complex algorithmic problems. We evaluate 11 randomly selected problem sets across seven open-weight LLMs using a tiered prompting strategy: contextless prompts, signature prompts providing structural anchors, and self-healing prompts utilizing iterative feedback from the Dafny verifier. To address vacuous verification, where models satisfy verifiers with trivial specifications, we integrate the uDebug platform to ensure functional validation. Our results show that while contextless prompting leads to near-universal failure, structural signatures and iterative self-healing facilitate a dramatic performance turnaround. Specifically, Gemma 4-31B achieved a 90.91% verification success rate, while GPT-OSS 120B rose from zero to 81.82% success with signature-guided feedback. These findings indicate that formal verification is now attainable for open-weight LLMs, which serve as effective apprentices for synthesizing complex annotations and facilitating high-assurance software development.

Chart-to-code generation demands strict visual precision and syntactic correctness from Vision-Language Models (VLMs). However, existing approaches are fundamentally constrained by data-centric limitations: despite the availability of growing chart-to-code datasets, simply scaling homogeneous chart-code pairs conflates visual perception with program logic, preventing models from fully leveraging the richness of multimodal supervision. We present CharTide, a novel data-centric framework that systematically redesigns both training and alignment data for chart-to-code generation. First, we construct a 2M-sample dataset via a Tri-Perspective Tuning strategy, explicitly decoupling training into visual perception, pure-text code logic, and modality fusion streams, enabling a 7B model to surpass specialized baselines using only supervised data. Second, we reformulate alignment as a data verification problem rather than a heuristic scoring task. To this end, we introduce an Inquiry-Driven RL framework grounded in the principle of information invariance: a downstream model should yield consistent answers to identical visual queries across both original and generated charts. Moving beyond rigid rule matching or VLM scoring, we employ a frozen Inspector to objectively verify generated charts through atomic QA tasks, providing verifiable reward signals based on answer accuracy. Experiments on ChartMimic, Plot2Code, and ChartX show that CharTide-7B/8B significantly outperforms open-source baselines, surpasses GPT-4o, and is competitive with GPT-5.

Generative Artificial Intelligence (GAI) systems that can automatically generate content in the form of source code or other contents (e.g., images) has seen increasing popularity due to the emergence of tools such as ChatGPT which rely on Large Language Models (LLMs). Misuse of the automatically generated content can incur serious consequences due to potential harms in the generated content. Despite the importance of ensuring the quality of automatically generated content, there is little to no approach that can systematically generate tests for identifying software harms in the content generated by these GAI systems. In this article, we introduce the novel concept of ethics testing which aims to systematically generate tests for identifying software harms. Different from existing testing methodologies (e.g., fairness testing that aims to identifying software discrimination), ethics testing aims to systematically detect software harms that could be induced due to unethical behavior (e.g., harmful behavior or behavior that violates intellectual property rights) in automatically generated content. We introduced the concept of ethics testing, discussed the challenges therewithin, and conducted five case studies to show how ethics testing can be performed for generative AI systems.

Large language models (LLMs) have recently shown strong potential for generating project-level unit tests. However, existing state-of-the-art approaches primarily rely on execution-path information to guide prompt construction, which is often insufficient for complex software systems with rich inter-class dependencies, deep call chains, and intricate object initialization requirements. In this paper, we present CAT, a novel call-chain-aware LLM-based test generation approach that explicitly incorporates call-chain and dependency contexts into prompts through dedicated static analysis. To construct executable, semantically valid test contexts, CAT systematically models caller--callee relationships, object constructors, and third-party dependencies, and supports iterative test fixing when generation failures occur. We evaluate CAT on the widely used Defects4J benchmark and on four real-world GitHub projects released after the LLM's cut-off date. The results show that, across projects in Defects4J, CAT improves line and branch coverage by 18.04% and 21.74%, respectively, over the state-of-the-art approach PANTA, while consistently achieving superior performance on post-cutoff real-world projects. An ablation study further demonstrates the importance of call-chain and dependency contexts in CAT.

Data is a central resource for modern enterprises, and data validation is essential for ensuring the reliability of downstream applications. However, existing automated data unit testing frameworks are largely task-agnostic: they validate datasets without considering the semantics and requirements of the code that consumes the data. We present PrismaDV, a compound AI system that analyzes downstream task code together with dataset profiles to identify data access patterns, infer implicit data assumptions, and generate task-aware executable data unit tests. To further adapt the data unit tests over time to specific datasets and downstream tasks, we propose "Selective Informative Feedback for Task Adaptation" (SIFTA), a prompt-optimization framework that leverages the scarce outcomes from the execution of data unit tests and downstream tasks. We evaluate PrismaDV on two new benchmarks spanning 60 tasks across five datasets, where it consistently outperforms both task-agnostic and task-aware baselines in generating unit tests that reflect the end-to-end impact of data errors. Furthermore, we show that with SIFTA, we can automatically learn prompts for PrismaDV's modules that outperform prompts written by hand or generated from a generic prompt optimizer. We publicly release our benchmarks and prototype implementation.

The capabilities of AI-assisted coding are progressing at breakneck speed. Chat-based vibe coding has evolved into fully fledged AI-assisted, agentic software development using agent scaffolds where the human developer creates a plan that agentic AIs implement. One current trend is utilizing documents beyond this plan document, such as project and method-scoped documents. Here we propose GROUNDING$.$md, a community-governed, field-scoped epistemic grounding document, using mass spectrometry-based proteomics as an example. This explicit field-scoped grounding document encodes Hard Constraints (non-negotiable validity invariants empirically required for scientific correctness) and Convention Parameters (community-agreed defaults) that override all other contexts to enforce validity, regardless of what the user prompts. In practice, this will empower a non-domain expert to generate code, tools, and software that have best practices baked in at the ground level, providing confidence to the software developer but also to those reviewing or using the final product. Undoubtedly it is easier to have agentic AIs adhere to guidelines than humans, and this opportunity allows for organizations to develop epistemic grounding documents in such a way as to keep domain experts in the loop in a future of democratized generation of bespoke software solutions.

Prior work evaluates code generation bias primarily through simple conditional statements, which represent only a narrow slice of real-world programming and reveal solely overt, explicitly encoded bias. We demonstrate that this approach dramatically underestimates bias in practice by examining a more realistic task: generating machine learning (ML) pipelines. Testing both code-specialized and general-instruction large language models, we find that generated pipelines exhibit significant bias during feature selection. Sensitive attributes appear in 87.7% of cases on average, despite models demonstrably excluding irrelevant features (e.g., including "race" while dropping "favorite color" for credit scoring). This bias is substantially more prevalent than that captured by conditional statements, where sensitive attributes appear in only 59.2% of cases. These findings are robust across prompt mitigation strategies, varying numbers of attributes, and different pipeline difficulty levels. Our results challenge simple conditionals as valid proxies for bias evaluation and suggest current benchmarks underestimate bias risk in practical deployments.

Multi-agent systems are frequently employed for autonomous code generation, demonstrating strong utility in complex algorithmic problem-solving. Recent studies tackle the difficulty of producing functionally correct programs by leveraging simulation-guided planning and debugging, wherein language models step through execution traces to validate logic. Nevertheless, these methods rely heavily on human-authored public test cases to anchor the simulation and debugging cycles. Hand-crafting exhaustive input-output pairs creates a significant, labor-intensive bottleneck within the software development lifecycle. Since ground-truth examples are seldom accessible before actual implementation in real-world scenarios, this reliance limits existing approaches primarily to curated competitive programming datasets. Additionally, we demonstrate that depending on these public tests creates an "overconfidence gap," leading frameworks to overfit to basic examples and underperform on hidden test suites. Conversely, we note that external input samples are not an absolute requirement for successful code generation. We show that large language models possess the capability to autonomously construct valid inputs and simulate execution flows for self-correction. Building on this, we introduce DryRUN, a framework that removes the necessity for ground-truth data by enabling the LLM to iteratively plan, synthesize its own test inputs, and run simulated executions, thereby mitigating algorithmic overconfidence. Assessments using the LiveCodeBench v6 dataset (post-March 2025) reveal that DryRUN achieves comparable performance to CodeSIM, a state-of-the-art, test-dependent baseline. Notably, it does so entirely without public tests or external execution signals, all while decreasing overall output token usage.

Multi-domain detection of the machine-generated code snippets in various programming languages is a challenging task. SemEval-2026 Task~13 copes with this challenge in various angles, as a binary detection problem as well as attribution of the source. Specifically, its subtasks also cover generator LLM family detection, as well as a hybrid code co-generated by humans and machines, or adversarially modified codes hiding its origin. Our submitted systems adjusted the existing mdok approach (focused on machine-generated text detection) to these specific kinds of problems by exploring various base models, more suitable for code understanding. The results indicate that the submitted systems are competitive in all three subtasks. However, the margins from the top-performing systems are significant, and thus further improvements are possible.

This work presents a multi-layered methodology for efficiently accelerating multimodal foundation models (MFMs). It combines hardware and software co-design of transformer blocks with an optimization pipeline that reduces computational and memory requirements. During model development, it employs performance enhancements through fine-tuning for domain-specific adaptation. Our methodology further incorporates hardware and software techniques for optimizing MFMs. Specifically, it employs MFM compression using hierarchy-aware mixed-precision quantization and structural pruning for transformer blocks and MLP channels. It also optimizes operations through speculative decoding, model cascading that routes queries through a small-to-large cascade and uses lightweight self-tests to determine when to escalate to larger models, as well as co-optimization of sequence length, visual resolution & stride, and graph-level operator fusion. To efficiently execute the model, the processing dataflow is optimized based on the underlying hardware architecture together with memory-efficient attention to meet on-chip bandwidth and latency budgets. To support this, a specialized hardware accelerator for the transformer workloads is employed, which can be developed through expert design or an LLM-aided design approach. We demonstrate the effectiveness of the proposed methodology on medical-MFMs and on code generation tasks, and conclude with extensions toward energy-efficient spiking-MFMs.

What looks like acceleration can be a quiet transfer of burden from the present to the future. Attempts to replace human labor with AI systems are often presented as rational responses to technological progress, but that view is often structurally short-sighted. Across software development and adjacent knowledge industries, AI is increasingly attractive because it appears to reduce labor costs, speed output, and improve short-term metrics. Yet those gains may be achieved by drawing down human capabilities that are slow to build and difficult to restore. This paper develops a mechanism of capability masking and capability erosion under AI labor substitution. AI-generated output can create the appearance that organizational capability has been replaced, even when dependence on skilled human labor remains. That appearance can support hiring restraint while slower costs accumulate in the background. Evidence from AI-assisted coding shows that generated output still requires substantial human verification and remains uneven in correctness, maintainability, and security. Repository-level studies also suggest limits in handling broader codebase context. More broadly, labor-market, political-economy, and industrial-strategy evidence suggests that substitution pressures are being driven by managerial cost incentives and national competition while increasing risks of concentration and platform control. The result is a system that may look more efficient in the short term while becoming more fragile over time.

Small language models (1-3B) are practical to run locally, but individually limited on harder code generation tasks. We ask whether composing them into pipelines can recover some of that lost capability. We study code generation pipelines built from 1-3B models with execution feedback, and use a NEAT-inspired evolutionary search to test whether more complex pipeline structure helps beyond a simple refinement loop. We evaluate on HumanEval (164 problems) and sanitized MBPP (427 problems), all with local inference on a single laptop. Self-refinement with execution feedback improves code generation by more than 4 standard deviations on both benchmarks. The gains are narrow in mechanism: refinement fixes many runtime errors (especially NameError and SyntaxError), but rarely fixes logic errors such as AssertionError. Within our tested general-purpose model pool, generator identity mattered less than refiner capability: a 1.5B generator paired with a 3B refiner matched a 3B model doing both roles. Early stopping is essential; without it, every iteration is net-negative. The code-specialized models outperform every general-purpose pipeline configuration, suggesting model specialization matters more than pipeline architecture. Preliminary text-only pipeline experiments without execution feedback did not show gains at this scale. In our constrained search space, evolutionary search mostly rediscovered the same simple generate-execute-refine loop we found manually, with no clearly significant gain from added topology. Single-evaluation fitness inflates results by 5-7 percent, selecting lucky genomes over good ones. On these benchmarks at 1-3B scale, execution feedback mattered more than added pipeline complexity in determining whether composition helped.