AI Software Engineering

Recent work has demonstrated that coding agents can formalize entire advanced mathematics textbooks in Lean 4, yet existing efforts concentrate on branches of mathematics already well-represented in mathlib and measure success solely through kernel acceptance. We address both limitations by applying a coding agent to formalize Numerical Methods for Ordinary Differential Equations, a textbook in numerical analysis that is largely absent from mathlib, stressing the agent's capacity to develop new theory from scratch. We further introduce a systematic, reproducible three-dimensional framework for evaluating the quality of agent-produced formalizations beyond compilation: semantic correctness, Mathlib reuse, and cross-file reuse via LLM-as-judge methods. Applying this framework to our own formalization and to the released outputs of RepoProver and M2F, we uncover recurring unfaithful formalization patterns, including incomplete multi-part statements, added weakening hypotheses, and parameter restrictions, that kernel acceptance entirely obscures. Our results suggest that compilation-based metrics substantially overstate formalization quality, and we provide a reproducible audit methodology to support more rigorous evaluation of future autoformalization systems.

AI coding agents have rapidly transformed software engineering, powering widely used interactive coding assistants. Despite their interactive real-world use, existing benchmarks evaluate them as fully-autonomous systems. In this work, we introduce Dialogue SWE-Bench, an automatic benchmark dataset for evaluating the ability of coding agents to resolve real-world software engineering problems through dialogue with a user. We design a novel, persona-grounded user simulator to support our task evaluation, and augment our task evaluation with automatic evaluations of dialogue quality. We also propose a new schema-guided agent, aimed at improving the dialogue capabilities of off-the-shelf coding agents, which improves over strong baselines by 3-14%. Our results indicate that better coding models do not always correspond to better dialogue models, suggesting that dialogue capability is a distinct and currently understudied dimension of coding agent performance.

Automated International Classification of Diseases (ICD) coding is a core medical-coding task for billing, epidemiology, and clinical decision support. Generative large language models (LLMs) are often reported as weak medical coders, but this finding mainly comes from inference-time settings such as prompting, retrieval, reranking, or tool use, leaving the role of task-specific post-training underexplored. We present a controlled empirical study of post-training for generative ICD coding, comparing discriminative baselines with LLM coders across prompting, supervised fine-tuning, and reinforcement learning under a common protocol and metric set. To our knowledge, this is the first study to evaluate RL-based post-training for generative LLM coders in ICD coding. We further introduce PHI, a diagnostic curriculum that extends GRPO to refine missed-code cases. Our results show that prompting-only evaluation substantially underestimates the potential of LLMs for ICD coding. SFT provides the main capability jump, GRPO further improves code-set prediction beyond SFT, and PHI provides targeted gains on macro-level performance. These findings suggest that the main bottleneck is not the generative formulation alone, but how the model is adapted and optimized for full-taxonomy recall. We release our code, data splits, and checkpoints at https://github.com/AlexandreWANG915/LLM4ICD.

Large language models (LLMs) are increasingly deployed in automated code-review systems, where their approvals can determine which code is merged into shared repositories. However, it is unclear whether review agents can detect vulnerability-introducing code when an attacker controls both the code change and the persuasive Pull Request (PR) narrative designed to mask it. We introduce SEVRA-BENCH (Social Engineering of Vulnerabilities in Review Agents), a benchmark that measures how often a review agent approves such adversarial PR s. Each PR in SEVRA-BENCH is built from a historical commit that fixed a vulnerability. We automatically reverse that fix to extract the original vulnerable code, and submit the resulting code change as a PR wrapped in one of 15 social-engineering framings. To test review-agent resilience to narrative manipulation, these framings vary dimensions such as supporting evidence, conveyed urgency, signals of prior approval, and appeals to authority. SEVRA-BENCH evaluates a retained challenge split of roughly 1000 adversarial PRs drawn from publicly disclosed vulnerability fixes across the top 10 entries of the MITRE's 2025 most dangerous software weaknesses. Evaluating 8 review agents against this benchmark, we reveal that review agents are susceptible to narrative manipulation, exposing a significant gap in security capabilities.

AI coding agents are increasingly used to generate pull requests (PRs) that propose code fixes in software projects. From a first exploration of the AIDev dataset, we find that 46.41% of the fixes proposed by the agents Copilot, Devin, Cursor, and Claude are rejected. This represents a significant amount of wasted resources that require human reviews, verifications, and running tests and validations for fixes that are merely discarded. Our goal in this paper is to understand the failure modes of AI-agents, an understanding that is crucial for better integrating AI-agents as efficient teammates. In this paper, we conduct a qualitative study on a representative sample of 306 non-merged pull requests created or co-authored by the agents mentioned earlier, followed by a quantitative analysis of the reasons for rejection. Our qualitative findings identify 14 reasons divided into four high-level categories for rejecting AI-agent fixes. We observe that developers can reject fixes due to fixes whose implementation is incorrect (e.g., incomplete, wrong approach), fixes that do not pass the continuous integration (CI) pipelines and fail tests, fixes for which the agent is unable to perform the implementation (e.g., no code generated, sessions lost), and fixes whose priority is low. Our results shed light on the importance of better guiding the model at these levels: (1) proposing hints about the approach to follow for fixing an issue, (2) outlining constraints or limitations regarding the approaches that should not be taken, and (3) instructing the agent on how to validate the implementation through CI pipelines and without introducing a breaking change. Our results suggest the need for good prioritization of tasks so that generated fixes do not lead to wasted human review efforts or wasted agent resources (e.g., tokens, compute, or allowed number of requests).

AI-agents (e.g., GitHub Copilot) collaborate as teammates in different software engineering tasks, including code generation proposed through pull requests (Agentic-PRs). For better agent efficiency, developers create instruction files that guide the AI-agents, including how to navigate the project, locate the right components, run tests, respect best practices, and more. In this paper, we investigate the relationship between the creation of these instructions and the performance of AI-agents in creating better pull requests, which have a higher chance of success (i.e., the merge rate), address more complex tasks (e.g., code churn), and require less effort to be merged (e.g., time to merge). To this end, we analyze 15,549 agentic PRs from 148 projects in the AIDev dataset. Using the three dimensions, we compare each project before and after the creation of the instruction files. We find that specifying instructions for AI-agents does not necessarily lead to better results. With the instruction files, 27.7% of the projects increased their merge rate by at least 20%, while 26.35% decreased it. The same observation is seen with the amount of changes (e.g., code churn, number of modified files) and with the efforts to merge an agentic PR (e.g., merge time and number of comments). From a first exploration, we find that projects that managed to increase their merge rate have substantially longer instruction files, which are also well structured into a higher number of sections and sub-sections. Our results motivate the need for research to assist practitioners in framing the development of instruction files as a software engineering activity (aka, \textbf{Instructions-as-Code}).

Computer-Aided Design is pivotal in modern manufacturing, yet existing automated methods predominantly rely on open-loop, one-shot generation, creating a mismatch with iterative real-world practices. In this paper, we present IterCAD, a unified multimodal agent framework for closed-loop, interactive CAD generation and editing. We formulate the task as a multi-turn interaction between a multimodal agent and an executable CAD sandbox, covering three tasks: Drawing-to-Code, Text-to-Code, and Interactive Editing. To support this, we develop a data synthesis pipeline incorporating advanced industrial manufacturing features to generate standard-compliant multi-view engineering drawings, complex code-editing tasks, and high-fidelity interaction trajectories. We optimize the agent via progressive SFT followed by geometry-aware reinforcement learning with viable-prefix masking to enhance code executability and geometric fidelity. Finally, we introduce the IterCAD-Bench evaluation suite and propose the Chamfer Distance Tolerance-Recall (CD-TR) curve alongside its AUC-TR metric, establishing a survivor-bias-free standard that unifies code validity and geometric precision. Extensive experiments demonstrate that IterCAD achieves highly competitive performance across multiple benchmarks, significantly outperforming existing approaches in both code executability and geometric precision, while exhibiting superior capabilities in closed-loop iterative refinement.

AI coding tools are now used by a majority of developers, and agentic use of these tools has popularized the practice colloquially called "vibe coding". Yet causal evidence on their effect on software architecture is scarce. Prior causal work has measured code-level outcomes (complexity, static analysis warnings); whether such degradation propagates to architecture-level outcomes remains unknown. We mine 151 open-source Java repositories, 74 with detectable agentic AI adoption (identified via configuration files and Co-Authored-By commit trailers) and 77 propensity-matched controls, across a 13-month per-repository window yielding 1,811 monthly Arcan snapshots. We estimate the causal effect of adoption on architectural smell density (ASD) with a staggered difference-in-differences design and the Borusyak imputation estimator, applying a causal design recently used for code-level metrics to the architecture level. Total smell counts are essentially unchanged (+1.1%, p = 0.82) while lines of code grow +12.8% (p = 0.003); the resulting 6.7% ASD decline (p = 0.004) is therefore a denominator effect rather than an architectural improvement. Per-type estimates and robustness checks (wild cluster bootstrap, Lee bounds, stale-observation sensitivity) corroborate the pattern; pre-trends are flat (Wald p = 0.90), consistent with parallel trends. Density-normalized outcomes can mislead when treatment affects system size: raw counts and explicit decomposition are required for causal mining studies of AI tool adoption. The complete replication package, including the curated 151-repository monthly panel, is publicly available.

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

As AI-generated reviews move from experimental tools into peer-review infrastructure, most robustness concerns have focused on explicit attacks such as hidden instructions and prompt injection. We study a harder and more policy-relevant failure mode: no hidden text, no prompt injection, and no changes to methods, experiments, figures, equations, proofs, or numerical results. The attacker modifies only presentation-level content, such as the abstract, contribution framing, related work, discussion, and narrative structure. We introduce adversarial repackaging: a closed-loop attack that uses AI-reviewer feedback to search for presentation-level revisions while keeping the scientific evidence fixed. Across three mainstream AI reviewers, adversarial repackaging achieves a 75.1% attack success rate and a mean score gain of +1.21/10. The effect is not explained by ordinary prose polishing. We also reveal that strategies that change how the reviewer interprets the paper, such as related-work repositioning and analytical discussion expansion, substantially outperform surface edits such as local polishing, table formatting, and algorithm boxes. Our analysis reveals two deeper structural failure modes. First, AI reviewers are easier to impress than to convince: highlighting strengths reliably increases perceived merit, while attempts to dissolve weaknesses frequently backfire. Second, AI reviewers can confuse the appearance of addressing a limitation with actually resolving it, allowing unchanged evidence to be reinterpreted as stronger scientific contribution. These results show that the deployment risk is not only malicious hidden instructions, but the emergence of paper presentation itself as an optimization surface. We release a contamination-free rolling benchmark and attack framework for testing whether AI reviewers remain anchored to scientific content under presentation-only edits.

Automated testbench generation has become a critical bottleneck in large language model (LLM)-driven Register Transfer Level (RTL) workflows, where large numbers of candidate designs must be verified rapidly and reliably. Existing prompt-based approaches treat testbench generation as unconstrained code synthesis, yielding stochastic outputs with high token cost, low reproducibility, and insufficient coverage. To address this gap, we present STG, a Structured Testbench Generation framework that exploits the inherent structure of hardware designs to generate deterministic testbenches. As a direct verification tool, STG runs 720x faster than an iterative LLM-based testbench generation flow and higher rate of successful compilation, achieves higher coverage, and reduces false-pass verdicts on incorrect DUTs. STG also helps identify errors in RTL generation benchmarks by exposing faulty benchmark testbenches. As a data curation engine, it is 11x faster than LLM-based filtering on a single CPU core with 127x less energy, and the resulting distilled models provide state-of-the-art performance in our multi-benchmark evaluation. As a test-time scaling oracle, it reduces node count by 14-47%. Our models are available at https://huggingface.co/collections/AS-SiliconMind/siliconmind-v12.

Molecular dynamics (MD) is the canonical in-silico method for atomistic molecular science, simulating molecular behavior from first-principle physics. Designing an MD pipeline for a new system requires substantial expert knowledge: running it on even one molecule is expensive, ruling out trial-and-error. We automate this expert pipeline-design process with an LLM agent. Unlike existing MD agents that orchestrate a predefined tool set, we treat pipeline design as open-ended code generation in which the agent's behavior is reshaped online by verbal reward. Specifically, we build MDForge, an LLM agent whose in-context update rule densifies the sparse reward via a multi-agent debate among physics experts. On three SAMPL host-guest binding free-energy benchmarks, MDForge automatically designs MD pipelines competitive with human experts. Deployed on a library of unseen candidate guests, its CB[7] pipeline discovers a novel binder that wet-lab competition NMR confirms is a high-affinity, picomolar CB[7] binder. Our data and code are available at https://github.com/Zehong-Wang/MDForge.

Despite strong performance in competitive programming, the role of Large Language Models (LLMs) in supporting human learning in the same setting remains largely unexplored. In this work, we introduce UOJ-Bench, a benchmark designed to evaluate not only the problem-solving ability of LLMs, but also their ability to identify errors in human-written code -- a crucial educational activity traditionally supported by running test cases over online judge systems. UOJ-Bench consists of three distinct tasks: code generation, code hacking, and code repair, all constructed from real-world code submissions on the Universal Online Judge (UOJ) and evaluated through UOJ's native judging infrastructure. Our results show that under one-shot evaluation, even the strongest models fail to identify errors in more than 50% of a set of submissions that have been found to be incorrect by UOJ users. While test-time scaling improves success rates to above 90%, the substantial computational costs incurred from model inference limit its practicality for large-scale deployment. Despite these limitations, we find that the best-performing models under test-time scaling can uncover errors in over 5% of full-score submissions across roughly 30 problems, suggesting that frontier LLMs can already provide complementary signals beyond standard judging systems.

Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources. Existing defenses mainly focus on blocking malicious content at inference time, and current red-teaming methods primarily optimize attack success. As a result, developers have limited visibility into how latent prompt injections emerge and propagate through agents. We propose PI-Hunter, an automated agentic auditing framework for proactive vulnerability exposure in LLM agents. PI-Hunter constructs realistic source-aware test cases and iteratively evolves them through feedback-driven exploration to induce agents to retrieve and reveal latent malicious instructions embedded within external environments. Extensive experiments across multiple benchmarks, agent architectures, attacks, and defenses demonstrate that PI-Hunter substantially improves vulnerability exposure and attack-surface coverage over strong automated red-teaming baselines, while remaining effective under existing prompt injection defenses.

Thanks to the rapid adoption of AI code assistants powered by large language models (LLMs), industry codebases are, increasingly, a hybrid of AI- and human-authored code. For risk management and productivity analysis purposes, it is crucial to enable fine-grained location detection of AI-generated code. To develop algorithms for this task, quality benchmarks are needed to assess performance. However, existing benchmarks tend to comprise academic, LeetCode-style problems and presume a code snippet is either completely human-authored or completely AI-authored, which is not reflective of the diverse intents and styles of industry codebases utilizing AI code assistants. To fill these gaps, we introduce HybridCodeAuthorship, a novel benchmark of Python code files with interleaved human- and AI-authored lines of code to simulate authentic utilization of AI code assistants. In this paper, we first present our dataset construction pipeline, which leverages CodeSearchNet, a massive collection of links to open sourced repositories on GitHub. We then benchmark the performance of two state-of-the-art AI-generated code detection algorithms at both the line- and chunk-level. Experimental results demonstrate that HybridCodeAuthorship is a challenging benchmark with a top-scoring algorithm, AIGCode Detector, obtaining a highest F1 score of 0.48 and 0.56 on chunk-level and line-level code detection tasks, respectively.

General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and prediction contract required for scoring. We introduce Claw-SWE-Bench, a multilingual SWE-bench-style benchmark and adapter protocol that makes heterogeneous agent harnesses, or claws, comparable under fair settings including a fixed prompt, runtime budget, workspace contract, patch extraction procedure, and evaluator. The full benchmark contains 350 GitHub issue-resolution instances across 8 languages and 43 repositories, drawn from SWE-bench-Multilingual and SWE-bench-Verified-Mini after future-commit cleanup. We also release Claw-SWE-Bench Lite for faster validation, which is an 80-instance subset selected by a cost-aware, rank-aware procedure over 17 calibration columns. On the full benchmark, OpenClaw with a minimal direct-diff adapter scores only $19.1\%$ Pass@1, whereas the full adapter reaches $73.4\%$ with the same GLM 5.1 backbone, showing that adapter design is essential for enabling OpenClaw-style harnesses to perform coding tasks effectively. Across an OpenClaw $\times$ nine-model sweep and a five-claw $\times$ two-model sweep, model choice changes Pass@1 by $29.4$ pp and harness choice by $27.4$ pp under fixed models; systems with similar accuracy can differ substantially in total API cost. Claw-SWE-Bench therefore treats harness and cost accounting as first-class axes of SWE-style coding-agent evaluation, providing both a full benchmark and a low-cost reference set for reproducible comparison. The data is available at https://github.com/opensquilla/claw-swe-bench and https://huggingface.co/datasets/TokenRhythm/Claw-SWE-Bench.

AI coding assistants now support a growing share of software work, from quick scripts to production applications. Yet these agents remain largely stateless: each new session re-reads project files, re-derives prior decisions, and - most costly - may repeat debugging attempts that already failed. Reconstructing this context can consume an estimated 5,000-20,000 tokens per session; the bottleneck is often not model capability but missing project memory. We present projectmem, an open-source, local-first memory and judgment layer for AI coding agents. projectmem records development as an append-only, plain-text event log of typed events - issues, attempts, fixes, decisions, and notes - and deterministically projects that log into compact, AI-readable summaries served through the Model Context Protocol (MCP). Beyond storage, projectmem adds a deterministic pre-action gate that warns an agent before it repeats a previously failed fix or edits a known-fragile file. We frame this as Memory-as-Governance: memory that does not merely answer the agent but acts on its next action. The system runs fully offline with no telemetry; its immutable log also serves as a provenance trail for reproducible, auditable AI-assisted development. projectmem ships as a three-dependency Python package (14 MCP tools, 19 CLI commands, 37 automated tests) and is evaluated through a two-month self-study across 10 projects comprising 207 logged events. Source code: https://github.com/riponcm/projectmem.

The adoption of AI-powered Integrated Development Environments (AI IDEs) has introduced "Rules" as a novel software artifact, allowing developers to persistently inject project-specific constraints and architectural guidelines into the context of Large Language Models (LLMs). Despite their role in aligning AI behavior with developer intent, the taxonomy, evolution, and practical impact of these rules remain largely unexplored. To bridge this gap, we conducted a mixed-methods empirical study on AI IDE rules. By mining 83 open-source projects and extracting 7,310 rules, we established a comprehensive taxonomy comprising 5 primary and 25 secondary categories. We then triangulated these artifacts with survey responses from 99 practitioners. Our analysis identified a contrast between developer priorities and actual configurations: while practitioners rate architectural constraints as highly important, rule files in repositories primarily consist of low-level workflow and code formatting constraints. Furthermore, our analysis of 1,540 rule evolution events revealed that rules are updated frequently. Repository data further indicate that rule evolution is primarily driven by constructive context expansions (29.17%) and enrichments (26.59%). In contrast, surveyed developers reported modifying rules primarily to correct AI errors (77.78%), typically by adding new negative constraints rather than editing existing ones. Finally, an artifact compliance assessment of 160 rule evolution events revealed that updating rules significantly improves the adherence of software artifacts, with the average artifact compliance rate increasing by 22.99% (from 49.14% to 72.13%) following an update. Our study provides empirical insights that can help developers optimize prompting strategies and guide tool builders in designing automated conflict-detection and context-management mechanisms for AI IDEs.

Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repositories linearly, that is, visiting one directory or file per step. We postulate that this is a structural mismatch for changes that span several subsystems. We compare linear sequential exploration against non-linear, domain-scoped parallel agentic exploration. Using SWE Bench Pro as initial benchmark, we focus on ansible as an exemplar. We construct an approach for persistent-session evaluation of GitHub issues anchored at a single base commit. We compare our non-linear domain-agent file traversal system against a base LLM without direct repository access, a single agent Recursive Language Model (RLM) baseline with a persistent Python REPL and an external CLI baseline using Codex 5.5 High. Domain scoped parallel agent spawning with a small Haiku-class model achieves the highest micro F1 among Haiku class models by a large margin. Domain-agents is the second highest behind only the much larger Codex 5.5 High on our own expanded benchmark including over more recent PRs from 2025 and 2026. On the original, curated, 2020 SWE-bench Pro benchmark, a larger Sonnet plain LLM baseline attains higher micro F1 by predicting few files, leading to higher precision, but at significantly lower all gold recall. We also present three additional findings. First, documentation evolution is a latent dependency unresolved by any approach. Second, naive file system access can degrade localization driven by test-file over prediction. Lastly, forced multi-agent consultation does not measurably help and raises token cost substantially.

This paper proposes an empirical methodology to study software aging in GPU-based LLM serving systems. Traditional aging studies focus on CPU-centric software with relatively regular workloads; LLM serving is different, spanning a Python host and a CUDA device, handling requests whose cost varies by orders of magnitude, and relying on rapidly evolving software stacks. We run a 216-hour campaign across six co-located deployments under identical stress conditions, monitor host, device, and client metrics in parallel, and apply a statistical pipeline that accounts for autocorrelation and multiple testing. Our results reveal statistically significant memory aging in all deployments, with leak rates strongly dependent on the serving runtime and deployment configuration. Beyond these findings, we provide a reproducible framework that opens a research direction at the intersection of the software aging and rejuvenation and LLM serving communities.

Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decoding (GCD) has been widely adopted to improve the reliability of LLM-generated code by enforcing syntactic validity. In this paper, we reveal a counterintuitive risk: this reliability-oriented technique can itself become an attack surface. We uncover a new jailbreak attack, termed CodeSpear, that exploits GCD to induce LLMs into generating malicious code. Our experiments show that simply applying a benign code grammar constraint can effectively jailbreak LLMs. To address this vulnerability, we propose CodeShield, a safety alignment approach that robustly preserves safe behavior even under attacker-controlled grammar constraints. CodeShield aligns the model in the code modality by teaching it to generate honeypot code under GCD. Such code is semantically harmless, so it does not implement the malicious request, and structurally diverse, so it is difficult to suppress through grammar tightening. At the same time, CodeShield still preserves natural-language refusals when natural language is available. Experiments on 10 popular LLMs across 4 benchmarks show that CodeSpear outperforms representative jailbreak baselines and increases the attack success rate by more than 30 percentage points on average. CodeShield also restores safety under CodeSpear while preserving benign utility. Our findings reveal a fundamental risk of GCD and call for greater attention to its potential security implications.

Supervised fine-tuning of code LLMs typically applies uniform cross-entropy loss to all response tokens, implicitly assuming that every token provides equally useful learning signal. Recent token-level selection methods challenge this assumption in natural-language SFT by supervising only high-value tokens. However, directly transferring token-level masking to code can break syntactically and semantically coherent program units, because code depends on structural completeness and definition-use relations. We therefore propose CodeBlock, a structure-aware sparse supervision framework that selects structure-complete code evidence rather than isolated tokens. CodeBlock first selects high-quality instruction-response pairs, then partitions code responses into syntactically coherent coding items, estimates their utility by aggregating generalized cross-entropy over core logic tokens, and reranks them with data-flow reach and bridge signals to prioritize blocks that propagate or connect important program dependencies. During training, the full response remains available as context, while loss is applied only to selected code items and informative natural-language tokens. Experiments on six code-generation benchmarks show that CodeBlock achieves stronger average pass@1 than full-token SFT and competitive selection baselines, while using only 1.9% of supervised response tokens.

Financial and tabular question answering requires more than fluent reasoning: answers must be grounded in the exact facts, formulas, units, signs, and scales that support them. A single misread cell or incorrect operation can silently produce a plausible but wrong result. We introduce \textsc{MOCA-Agent}, a market-of-claims code agent that replaces free-form multi-agent debate with claim-level verification. The system decomposes each question into typed atomic claims, asks specialist trader agents to buy or sell those claims, clears their orders into confidence-weighted accept/reject decisions, and synthesizes an executable Python program from market-supported evidence. A code-aware verifier then checks the program for execution, structural consistency, and common financial reasoning errors, with at most one market-aware repair round. Across ten public benchmarks spanning financial numerical reasoning, general tabular reasoning, ESG question answering, and multimodal chart reasoning, \textsc{MOCA-Agent} achieves strong performance using a fixed Qwen3.6-27B backbone, including $78.3\%$ on FinQA, $76.0\%$ on FinanceMath, $71.2\%$ on MultiHiertt, $86.9\%$ on ESGenius, and $85.6\%$ average on FinChart-Bench. These results show that aggregating evidence at the level of atomic claims, rather than whole answers, improves robustness in high-stakes numerical reasoning.\footnote{The code and data are available: https://github.com/UBC-NLP/MoCA-Agent.

The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may reduce methodological diversity, or that they may amplify the analytic flexibility through which researchers reach motivated conclusions. We argue these worries target two empirically separable layers: a design layer of methodological choices, and a verdict layer in which a decision rule maps estimates to a substantive claim. We test both by running 20 independent executions of Claude Code and Codex on a prominent immigration and social-policy against a many-analysts human baseline. At the design layer, Codex matches human methodological diversity and Claude Code produces nearly three times as many specifications; both agents' effect estimates remain broadly aligned with the human consensus, and no agent model exactly matches any human model. A prompt-induced anti-immigration researcher prior reorganizes each agent's methodological decisions but, unlike for biased human analysts in the same data, does not shift aggregate estimates or final verdicts; nor do agents reroute along the methodological axes humans use to bias their estimates. At the verdict layer, an explicit confirmatory prompt flips Claude Code's verdicts from 10% to 90% support while leaving its coefficient distribution essentially unchanged, operating through rule omission rather than rule softening. AI agents can rival or exceed human methodological diversity at the design layer while remaining vulnerable at the verdict layer. In our setting, the locus of AI bias is not estimation but interpretation.

Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic evaluation across social sciences remains limited. Existing evaluation benchmarks are insufficient, either small or conflate agent performance with problems in the reproduction materials themselves, such as code that fails to execute correctly. Here we introduce SocSci-Repro-Bench, a benchmark of 221 tasks spanning four disciplines and 13 substantive domains, constructed from studies whose results are either fully reproducible with available materials or demonstrably non-reproducible due to missing data, allowing us to isolate agents' reproduction capacity. Evaluating two frontier coding agents, Claude Code and Codex, we find that both can reproduce a large share of social science findings, with Claude Code substantially outperforming Codex. These reproduction rates considerably exceed those previously reported for general-purpose LLM-based agents on comparable reproducibility benchmarks. Both agents also perform strongly on a reasoning task requiring identification of underlying research questions, and additional analyses suggest that results are not primarily driven by memorization. Providing the original paper PDF alongside replication materials modestly improves performance but introduces bias on tasks where reproduction is impossible. We also show that agents can be nudged toward confirmatory specification search through subtle prompt framing. Together, these findings suggest that at least some frontier coding agents can serve as reliable executors of computational workflows while underscoring the need for careful benchmarking and prompt design as AI systems assume larger roles in scientific production.

LLM-based coding agents are usually evaluated in familiar software settings: mainstream languages, common libraries, and public repositories. These benchmarks remain important, but they can hide how agents behave when the language itself is unfamiliar. We evaluate six contemporary coding agents on four esoteric programming languages using a sequential setup with file editing, local execution, and hidden-test grading. Our protocol exposes capability differences between these agents that mainstream coding and agentic benchmarks such as SWE-Bench Verified and Terminal-Bench 2.0 compress into much narrower bands. We observe that the strongest agents, Claude Opus 4.6 and GPT-5.4 xhigh, often avoid writing the target language directly. On Brainfuck and Befunge-98, they write Python programs that generate target-language code and debug those generators locally. Forbidding this metaprogramming strategy causes large performance drops. Text guidance distilled from this strategy does not materially improve weaker agents. In contrast, Opus-derived Python helper code for building generators, with no solved benchmark programs or hidden-test answers, sharply improves Sonnet 4.6 and GPT-5.4 mini on the same problems, while Haiku 4.5 remains low. More interpreter calls and output tokens improve stronger agents but leave weaker agents near their original performance, indicating that these resources amplify useful strategies rather than create them. Together, these results show that strong coding agents adapt to unfamiliar languages by using tools, feedback, and workspace state to build a working model of the target language. Metaprogramming is the clearest case, but the broader gap is constructing and debugging a strategy that works under the target language's rules.

Code-generating large language models (LLMs) increasingly produce visual artifacts such as charts, web pages, and slides by writing programs that are executed by non-differentiable renderers, committing to code before observing the render. As a result, otherwise executable code often yields artifacts with visually salient defects, including overlapping elements, clipped text, broken alignment, low contrast, and overflow. We study visual-feedback self-distillation for code-generated visual artifacts. We propose Visual-SDPO, a self-distillation policy-optimization framework that treats rendered visual feedback as privileged context for a weight-sharing teacher and distills this feedback into a coding student. To make supervision spatially targeted rather than uniform, we introduce Visual-Grounded Code Credit Weighting, which traces each detected defect back to the code statements responsible for the affected elements and amplifies the distillation signal on those statements. A sequence-level GRPO (Group Relative Policy Optimization) term complements the dense token-level objective by rewarding executable, visually high-quality rollouts, while failed executions remain learnable through the self-distillation path by passing execution errors as privileged context to the teacher. We instantiate Visual-SDPO for chart, web/UI, and slide generation with a unified Qwen3-VL-8B-Instruct backbone. Across chart-to-code, UI-to-code, and slide-generation benchmarks (ChartMimic, Design2Code, and AeSlides), Visual-SDPO improves over the zero-shot base by more than 10 absolute points in the primary metric and over GRPO by at least 2.4 points, with fewer training steps and no added inference-time cost.

Multi-agent code generation offers a promising paradigm for autonomous software development by simulating the human software engineering lifecycle. However, system reliability remains hindered by LLM hallucinations and error propagation across interacting agents. While semantic entropy provides a principled way to quantify uncertainty without ground-truth answers, current methods often rely on costly LLM-driven equivalence checks. In this work, we introduce Fast Adaptive Semantic Entropy (FASE), a novel metric that approximates functional correctness based on the minimum spanning tree of structural and semantic dissimilarity graphs. Evaluations on HumanEval and BigCodeBench demonstrate that FASE outperforms state-of-the-art semantic entropy by LLM entailment, achieving a 25% average improvement in Spearman correlation and a 19% increase in ROCAUC score against Pass@1 from ground-truth test cases when using the Qwen3-Embedding-8B model. Furthermore, by eliminating costly LLM-driven equivalence evaluation, FASE incurs negligible computational overhead, requiring only approximately 0.3% of the runtime cost of traditional semantic entropy approaches. These results position FASE as a practical, cost-effective solution for optimizing uncertainty quantification in real-world multi-agent workflows.

Configuring an advanced scientific simulator, translating a modeling goal into a valid, runnable input deck, is a persistent bottleneck that costs domain scientists hours to days. Input decks are executable interfaces: simulator-specific vocabulary, cross-file references, schema constraints, and validation rules must align before a simulation can run. We show that this bottleneck can be substantially reduced with a lightweight adapter around an off-the-shelf coding agent, rather than a bespoke simulator agent. Coding agents already navigate files, edit code, run commands, and repair outputs; what they lack is the simulator's executable contract, and rebuilding the agent loop risks discarding harness-calibrated tool-use and self-correction behavior. We introduce SIGA, a coding-agent adapter that supplies this contract through retrieval, procedural memory, agent-callable validation, and validation-gated termination while leaving the model and loop frozen. Because this contract is small and external, SIGA also supports adapter self-evolution: prior trajectories can rewrite the adapter contents without modifying the underlying agent. On GEOS, a multiphysics subsurface simulator, SIGA's main gain is reliability: on harder held-out tasks it improves TreeSim from 0.720 to 0.789 and reduces across-run standard deviation by about 16x by preventing empty or invalid decks. In a human calibration, SIGA reaches in about five minutes the deck quality a domain expert reached in about three hours. Transfers to OpenFOAM and LAMMPS show the recipe is portable but interface-dependent: completion gates help when structural completeness is the bottleneck, while memory and retrieval help when value correctness is.

Large language models (LLMs) are increasingly deployed as code generators, where silently wrong programs pose real safety and reliability risks. Reliable uncertainty estimation (UE) is essential for selective prediction, human-in-the-loop review, and downstream agentic decisions. Yet most existing code UE methods are inherited from natural language (NL) generation and ignore properties that make code distinct. We argue that code differs from NL in three ways: a single wrong token can break an entire program (token fragility); algorithmic intent and concrete implementation can disagree independently (intent-code gap); and programs can be executed (executability). We instantiate these properties as three orthogonal uncertainty axes: lexical (Top-K token entropy), algorithmic (pseudo-code consistency), and functional (behavioral consistency). Across five code LLMs, our three-axis ensemble improves average AUROC from 0.696 for the strongest NL-derived baseline to 0.776 (+8.1 points). Notably, on Qwen3-14B, our single-pass Top-K token entropy matches the strongest multi-pass baseline while being over 3x cheaper; across models, it remains a competitive low-cost signal. These results suggest that code UE deserves code-specific design rather than direct NL ports.

The rapid adoption of LLM-powered code generation has dramatically accelerated software development, yet effective verification methods remain severely underdeveloped. Existing bug localization techniques are either prohibitively expensive, requiring minutes of agentic reasoning and thousands of generated tokens per file, and/or operate at coarse function-level granularity unsuitable for precise debugging. While works that focus on line-level granularity and are more light-weight are often limited in their performance or context size. We introduce a novel line-level bug localization approach that addresses these limitations through three key contributions: (1) a token alignment algorithm that overcomes fundamental tokenization challenges in previous work, (2) a lightweight multi-task LLM for bug localization (MLC) enabling efficient line-level bug classification, and (3) an optimized training recipe for multi-line prediction. Our method achieves state-of-the-art performance among similar setups on line-level bug localization with full-file context. At the same time we reach comparable performance to agentic approaches on Defects4J and PypiBugs benchmarks while reducing inference latency by orders of magnitudes, requiring only a single generated token per file. We further demonstrate strong generalization by introducing and evaluating on a small out-of-domain evaluation datasets in Python. We will open source our code, models, and datasets upon acceptance.

We present our submission to the CVPR 2026 Argoverse 2 Scenario Mining Challenge. Our system uses a four-stage pipeline: (1) autonomous code generation via a Claude Code agent powered by GLM~5.1, (2) iterative training set screening with Timestamp Balanced Accuracy threshold 0.8 to curate few-shot examples, (3) semantic code review by a separate Claude Code session, and (4) Qwen3-VL scene-level verification to filter false positives. We report results on the Argoverse 2 test set.

Generating novel, feasible, and high-quality research ideas is an important yet challenging task in scientific discovery. Recent Large Language Model (LLM)-based methods often ground idea generation with retrieved literature, but the retrieved evidence is usually provided as flat text, such as titles, abstracts, or summaries. Such flat contexts may contain redundant or weakly relevant information, while making cross-paper relations among problems, methods, mechanisms, and findings difficult to identify and trace. To address this challenge, we propose Graph2Idea, a knowledge graph-guided framework for retrieval-augmented scientific idea generation.Graph2Idea first retrieves papers according to the input topic, transforms them into structured knowledge triples, and dynamically constructs a target-centered knowledge graph to make literature relations explicit. It then extracts compact graph-derived contexts that retain target-relevant relational evidence while reducing noisy textual input. Based on these contexts, a two-stage generation process first identifies promising research directions and then guides the LLM to synthesize candidate ideas from graph-grounded evidence. Experiments on a scientific idea generation benchmark show that Graph2Idea outperforms representative baselines under the automatic evaluation protocol. Compared with the strongest baseline scores, it improves Novelty from 0.45 to 0.52, Quality from 0.24 to 0.29, and Feasibility from 0.22 to 0.28. These results suggest that graph-structured evidence helps LLMs generate research ideas through more explicit, compact, and traceable recombination of prior scientific knowledge.

Developers increasingly provide AI coding assistants with persistent context through configuration files such as CLAUDE.md, AGENTS.md, and .cursorrules. These files describe code elements, architecture, and development conventions, forming the context that guides AI tool behavior across sessions. As software evolves, this context can become stale, a phenomenon we call context rot. While AI configuration artifacts are new, the underlying consistency problem connects to decades of software documentation research. Researchers have built tools to check consistency between documentation and code, spanning README files, code comments, API documentation, architecture descriptions, and installation instructions. We argue that this existing toolbox is an immediate starting point for detecting context rot, and we present a research roadmap mapping documentation consistency approaches to corresponding problems in this new setting. As preliminary evidence, applying an existing README/wiki consistency checker to a statistically representative sample of 356 repositories identifies stale code element references in 23.0% of repositories, showing that traditional documentation consistency tools can already surface context rot.

Code generation models are typically compared using compact execution benchmarks and aggregate pass rates, but such summaries obscure how performance varies across programming languages, problem families, and failure modes. We present a large-scale, execution-grounded evaluation of 9 openly accessible LLMs specialized for coding on 2,707 free LeetCode problems across 12 programming languages. Our corpus contains 325,343 problem-model-language jobs, each linked to prompt metadata, extracted code, LeetCode execution outcomes, and static-analysis signals. The results show that current open models remain far from the human acceptance reference: the best model, Yi-Coder-9B-Chat, reaches 23.64% mean correctness, compared with a 57.2% human acceptance baseline. Rankings are also slice-dependent: Qwen2.5-Coder-14B-Instruct is strongest on hard problems and distinct-problem coverage, while Gemma-2-27B-IT achieves the highest all-language lint pass rate. Failure analysis shows that compile errors account for 63.25% of non-accepted best submissions, indicating that many failures occur before semantic correctness can be tested. Static quality further diverges from functional correctness. Together, these findings show that multilingual, artifact-preserving evaluation reveals tradeoffs hidden by single-language or single-metric leaderboards.

The quality of software engineering is still under a challenge due to disjointed processes between requirements, testing, and production, which hinders the opportunity to implement quality strategies in consecutive releases. Existing approaches tend to be fixed-model or single-optimization approaches and lack production feedback learning mechanisms. The paper at hand proposes a closed-loop reference architecture of continuous software quality intelligence with AI enhancements. The model synthesizes requirement feature mining, risk-based test prioritization, defect prediction, and production incident analysis as an element of a feedback-based pipeline. A limited feedback learning model is introduced that is used to propagate the production signal-based on defect severity and incident impact- to the following release to ensure stability, and the time. The method is evaluated using a semi-synthetic test dataset of 4,500 requirements, 27,049 test cases, 13,089 defects and 7,841 incidents in six release cycles. The experimental results show that the proposed system reduces the defect leakage by 0.19 to 0.13, increases the effectiveness of the detection system to 0.72 to 0.84, and shortens the test execution by up to 35 percent compared to the non-adaptive baselines. The changes are stable release to release. The findings indicate that through the integration of feedback-based learning in a closed-loop architecture, it can be continued to enhance quality process, which offers practical foundation of adaptive quality engineering of software.

Modernization of legacy scientific codes is often necessary to keep up with the ever-evolving changes in the compute resource ecosystem. Parallelization and migration from poorly supported software ecosystems are two of the most time-consuming activities in the research software engineering field. This paper presents our experience in the successful, two-phase AI-assisted modernization of NMAP-RKPM, a roughly 60,000-line, 3D explicit solid mechanics physics engine based on the Reproducing Kernel Particle Method (RKPM). We converted this single-threaded, Fortran based MPI application into a OpenMP-parallel C++ based MPI tool in the span of a few months. While Large Language Model (LLM) based tools on their own proved inadequate, we developed a highly structured "hand-holding" agentic AI methodology, like providing manually created examples, ensuring continuous buildability and limiting session scope, that was instead highly effective. The paper provides both the AI-assisted steps that were successful and the problems that we had to overcome, alongside the reasoning behind the chosen path.

AI coding assistants have significantly improved developer productivity by automatically suggesting code that aligns with user intent, and many of these tools are now integrated directly into Integrated Development Environments (IDEs). Developers interact with code in two distinct cognitive modes: Flow and Command. While developers require tools that directly complete or infill code in unfinished programs during Flow mode, they also need tools that can comprehend intentions expressed as natural-language instructions and convert them into executable code in Command mode. Although instruction-tuned Large Language Models (LLMs) dominate many application scenarios due to their abilities to infer and fulfill developers' intents, it remains unclear whether the same paradigm is equally suitable for different code-related tasks. Therefore, it is necessary to understand how instruction tuning affects the feasibility of CodeLLMs as coding assistants. To fill this gap, we conduct the first empirical study that uncovers a key trade-off caused by instruction tuning across programming modes, which we term the Instruction-Tuning Tax. Our results show that instruction tuning is not a free lunch: although instruction-tuned models are more capable of following instructions and leveraging structured guidance, these gains often come at the cost of weaker infilling performance. We further extend our study through both qualitative and quantitative analyses, including manual failure categorization, behavioral metrics that capture generation fidelity, and intermediate-checkpoint evaluation throughout the tuning process. Summarizing our results into seven findings and four implications, our study offers a new perspective on the development of AI-powered coding tools and highlights the need to carefully balance instruction-following ability with effective code generation assistance.

Software engineering agents (SWE agents) increasingly work through tool-mediated trajectories in real repositories, yet their behavior remains difficult to characterize in concrete, observable terms. These trajectories record tool use, intermediate reasoning, evidence selection, and self-directed stopping, but they do not by themselves explain why particular moves were chosen, what evidence was trusted, or when understanding was judged sufficient. This tension makes trajectory data both limited and valuable: faithful, replayable traces can become an empirical substrate for studying agent behavior when interpreted through disciplined observation. We introduce Ada, a scoped apparatus for repository-level code understanding. Ada enters real codebases through a bounded tool interface, allowing open-ended exploration to remain recordable as finite trajectories. Across this wild-but-bounded setting, Ada chooses where to look, what to read closely, when to consolidate partial understanding, and when to close its account of the repository. We project Ada's think-action chains through observation lenses that make navigation, evidence selection, synthesis, grounding, and stopping visible without reducing behavior to raw tool counts or speculating about hidden intent. Read together, these lenses produce behavioral profiles grounded in recorded movement through software worlds. Across 408 trajectories, spanning multiple models, repositories, task families, and launch conditions, the study shows how faithful digital traces can be transformed into disciplined, comparable projections of emerging SWE-agent mindset. The results expose differences in efficiency, trajectory diversity, epistemic grounding, and the limits of intervention, while providing a methodological foundation for observing SWE agent behavior in real codebases.

Graduate-level research reading report assessment creates a substantial labor burden for educators. While large language models (LLMs) hold great potential for automating academic grading, their reliability for this specialized task remains understudied, particularly regarding grading consistency, the lack of which represents a primary obstacle to educational fairness. This paper proposes a human-aligned LLM-assisted grading workflow and presents a case study based on 180 student submissions from a graduate advanced software engineering course. We evaluate two mainstream LLMs, Grok and GPT, in terms of grading consistency and alignment with human scores. We find LLMs exhibit distinct levels of intra-model consistency and significant inter-model grading inconsistencies, while simple ensemble approaches cannot improve alignment with human evaluation. Critically, continuous interaction history drives systematic drift in models' grading standards away from human expert scores. Our findings demonstrate LLMs' potential in reducing grading workload for educators in graduate education, while highlighting that indiscriminate LLM grading may introduce systemic unfairness, suggesting that specific operational practices are required to mitigate such disparities.

LLM-based coding agents sometimes acknowledge a problem in their own reasoning and then proceed anyway. We call this pattern strained coherence: a safety-relevant failure mode in which an agent has information that should change its behavior, states that information, and still acts against it. The pattern overlaps with verbalized reward hacking, where an agent names a tension between a task proxy and the underlying goal yet optimizes the proxy anyway. We give an operational definition, build a Claude Sonnet 4.6 judge that reads full trajectories and flags spans where the pattern occurs, and evaluate it on 44 Terminal-bench-2 trajectories using a Qwen3.5-35B-A3B backbone. Flagged trajectories fail 94% of the time versus 46% for unflagged trajectories (47-point gap, Fisher's exact p = 0.003; 46 points after excluding three prompt-embedded examples, p = 0.006). At matched selectivity, the detector reaches 94% precision versus 88% for a lexical discourse-marker baseline; the 10-trajectory intersection of the two methods has a 100% failure rate (Clopper-Pearson 95% CI [69%, 100%]). We replicate on Gemma4-31B with 43 trajectories: the overall signal is directionally consistent but not significant (20-point gap, p = 0.31), with attenuation driven largely by 13 trajectories with zero think content, where the detector has no substrate to analyze. In the high-verbosity Gemma tertile, the gap is +30 points; in the mid- and high-verbosity Qwen tertiles, it is +40 points each. The first flag appears at a median of 83-84% of elapsed trajectory time across both models, and the binary flag survives paraphrases that soften explicit conflict markers (8/8 trajectories). Unlike univariate predictors, the detector emits interpretable span-level output -- quoted acknowledgment, quoted action, and typed conflict -- showing what the agent saw and ignored.

LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-quality SWE tasks. Existing synthetic data methods typically create tasks through fixed mutation or bug-injection procedures, making the resulting distributions largely independent of the agent's own weaknesses and training progress. We introduce Socratic-SWE, a closed-loop self-evolution framework that reuses the agent's historical solving traces as a source of training signal. Rather than treating traces only as evidence for reward computation, Socratic-SWE distills them into structured agent skills that summarize recurring failures and effective repair patterns. These skills then guide the generation of targeted repair tasks in real repositories. Candidate tasks are checked through execution-based validation and scored with a solver-gradient alignment reward, so that the retained tasks are both verifiable and useful for improving the Solver. The updated Solver produces new traces, enabling the task curriculum to adapt over successive rounds. Across SWE-bench Verified, SWE-bench Lite, SWE-bench Pro, and Terminal-Bench 2.0, Socratic-SWE consistently improves over self-evolving baselines under the same compute budget, reaching 50.40% on SWE-bench Verified after three iterations. These results suggest that solving traces can serve as a scalable substrate for self-evolving SWE agents.

A growing failure mode in agent evaluation and training is that models can achieve high evaluation scores by exploiting shortcuts instead of solving the intended task, producing deceptive performance. This makes evaluation scores unreliable as measures of true task-solving ability. We propose CapCode, a framework for constructing coding datasets with randomized tests whose best achievable non-cheating performance is deliberately capped below one. This capped-performance design gives evaluation scores a clearer interpretation: scores substantially above the cap are implausible and therefore provide evidence of cheating. To prevent cheating, we propose CapReward, a reward design based on the CapCode principle to discourage optimization beyond the cap. Experiments across multiple datasets show that CapCode detects cheating while preserving performance ranking of models, and CapReward reduces cheating behavior, yielding models that better follow the intended task specification.

Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary prediction problem (e.g., resolved or unresolved), neglecting fine-grained agent capabilities such as repository understanding, context retrieval, code localization, and bug diagnosis. In this paper, we introduce SWE-Explore, a benchmark that isolates the evaluation of repository exploration, a critical capability of coding agents. Given a repository and an issue, SWE-Explore asks an explorer to return a ranked list of relevant code regions under a fixed line budget. SWE-Explore covers 848 issues across 10 programming languages and 203 open-source repositories. For each instance, we derive line-level ground truth from independent agent trajectories that successfully solved the same issue, distilling the specific code regions their solution paths actually consulted. We evaluate exploration along coverage, ranking, and context-efficiency dimensions, showing that these metrics strongly track downstream repair behavior. Across a broad set of retrieval methods, general coding agents, and specialized localizers, we find that agentic explorers form a clear tier above classical retrieval. While file-level localization is already strong for modern methods, line-level coverage and efficient ranking remain the key axes differentiating state-of-the-art explorers.

Automatic decompilers produce functionally correct but often unreadable C code. This paper addresses one stage of the reverse engineering workflow: improving the readability of decompiled code using LLM agents guided by quantitative metrics. We present a three-phase research evolution. Phase 1 (tool-driven steering via Ghidra MCP) suffered from incomplete coverage and inconsistent improvements due to lack of quantitative guidance. Phase 2 (structural similarity validation alone) revealed that agents optimize for metrics in unintended ways, producing structurally equivalent but less readable code. Our contribution is the Quantitative Readability Score (QRS) framework, a composite metric combining a structural similarity gate with three independent readability sub-metrics (Lexical Surprisal, Structural Simplicity, and Idiomatic Quality). We demonstrate that QRS-guided refinement enables LLM agents to make targeted readability improvements without sacrificing correctness. We provide a discussion of the broader reverse engineering workflow (binary lifting, decompilation cleanup, and achieving functional equivalence) as context, however, it remains out of scope.

Code language models need repository-level context to resolve imports, APIs, and project conventions. Existing methods inject this knowledge as long inputs (retrieved through RAG or dependency analysis) or through per-repository fine-tuning and LoRA -- costly at repository scale and brittle to evolving codebases. We introduce Code2LoRA, a hypernetwork framework that generates repository-specific LoRA adapters, effectively injecting repository knowledge with zero inference-time token overhead. Code2LoRA supports two usage scenarios: Code2LoRA-Static converts a single repository snapshot into an adapter, suitable for comprehension of stable codebases; while Code2LoRA-Evo maintains an adapter backed by a GRU hidden state updated per code diff, suitable for active development of evolving codebases. To evaluate Code2LoRA against parameter-efficient fine-tuning baselines, we build RepoPeftBench, a benchmark of 604 Python repositories with two tracks: a static track with 40K training and 12K test assertion-completion tasks, and an evolution track with 215K commit-derived training and 87K commit-derived test tasks. On the static track, Code2LoRA-Static achieves 63.8% cross-repo and 66.2% in-repo exact match, matching the per-repository LoRA upper bound; on the evolution track, Code2LoRA-Evo achieves 60.3% cross-repo exact match (+5.2 pp over a single shared LoRA). Code2LoRA's code can be found at https://anonymous.4open.science/r/code2lora-6857; the model checkpoints and RepoPeftBench datasets can be found at https://huggingface.co/code2lora.

Large language models increasingly write, review, and judge code, and a fast-growing practice equips them with prompt 'skills' that ask the model to reason like a scientist. A prominent example tells the model to act as a Popperian falsificationist, and such skills are reported to improve generated code. But these gains are almost always read off an LLM-as-a-judge, an instrument with documented positional, self-preference, and stylistic biases. We ask: if it appears to help, is the gain from the skill's Popperian content, or from the structure any scaffold imposes? We pre-register a two-tier ablation with three controls: a length-matched placebo, a labels-only scaffold that keeps the Popperian headers but strips the procedure, and an execution oracle (HumanEval+ unit tests), plus a vocabulary-halo sentinel and a same-model self-judge audit. On a frontier model (Claude Sonnet 4.6, N=163) all conditions sit near the benchmark ceiling and do not separate, so the pre-registered +5-point improvement is not supported (a ceiling-limited non-detection). On a small model (Qwen2.5-Coder-0.5B, N=164) structured arms lift best-of-eight correctness by 20-22 points, but the full skill shows no separable benefit over a labels-only scaffold (aggregate F@8=L@8 vs V@8=34.8%), and the placebo trails by only 2.4 points. A 0.5B self-judge applying the Popperian rubric does not beat random selection and concentrates 60% of its picks on one index. In the two settings tested, the skill's Popperian procedural content adds no separable execution-correctness benefit beyond a labels-only scaffold, so the gains track scaffold structure. We contribute a calibrated negative result and a reusable disambiguation protocol; the finding bounds an engineering claim about one prompt-skill family and is not an evaluation of Popperian methodology in general.

Software testing is critical for verifying that systems meet specified requirements, yet remains among the most time-consuming and expensive activities in development. Requirements-based test generation allows test cases to be derived early from requirements artifacts, but generating them directly from natural language is challenging due to inherent ambiguity and imprecision. Recent advances in AI, natural language processing (NLP), and large language models (LLMs) have made automating this pipeline increasingly feasible, while introducing new risks including hallucination, reduced traceability, and inconsistent evaluation. This survey addresses four research questions: what AI and NLP techniques have been proposed for generating test cases from natural language requirements; what tools and frameworks support these approaches; how generated test cases are evaluated; and what research gaps remain. Following Kitchenham and Charters' systematic review guidelines, we searched major scholarly databases spanning 2000-2025 and, after applying strict inclusion criteria, identified 21 primary studies. The literature is organized into three evolutionary eras, revealing that no existing approach simultaneously satisfies six key quality dimensions: automation, ambiguity handling, domain applicability, traceability, evaluation thoroughness, and hallucination control. The survey makes three main contributions: a three-era evolutionary synthesis of AI-based test generation; a six-criteria gap analysis showing no current approach fully addresses all quality dimensions; and four actionable research guidelines targeting hallucination, traceability, complexity sensitivity, and compliance.

Existing code-generation benchmarks score a single mapping from a complete prompt to a one-shot output. However, real web development is different. Users seldom write a full spec at the start; many requirements only become clear once they look at an intermediate result and react to it. We present Asuka-Bench, a benchmark that pairs underspecified user intent with multi-round refinement, grounded in browser-rendered behavior. Each task is resolved through a closed loop: a Code Agent generates a web project, a UI Agent executes test cases on the deployed site, and a User LLM turns evaluation outcomes into natural-language feedback for the next round. The benchmark comprises 50 web tasks with 784 evaluation criteria and 2402 expected outcomes. We benchmark 8 LLMs across 2 agent frameworks. The results separate models clearly: weighted Task Pass Rate varies by 38 percentage points and models also differ substantially in their ability to repair from feedback. Asuka-Bench is also far from saturated: even the strongest model completes only 52% of projects after three rounds.

AI is changing how software engineers work, but it often comes with hidden burdens and costs. In this paper, we characterize two such often-overlooked burdens: (1) the constant need for human oversight and inspection of AI-generated artifacts; and (2) the growing cognitive overload on software engineers from receiving large amounts of suggestions from AI tools. The need for human oversight is not optional-engineers must review, validate, and sometimes rework what AI produces. At the same time, the flood of AI suggestions, prompts, and possible solutions can leave developers mentally stretched. By blending evidence from recent opinions from practitioners, we highlight these often-overlooked challenges and open a conversation about how teams can handle them in day-to-day AI-assisted software engineering.

Large language models and AI coding agents have reshaped software development, but the path to fully AI-native systems faces structural challenges. Chief among them is managing context windows without losing accuracy or efficiency. When developers inject full project documentation and code into a model's memory, the model loses mid-sequence information, token costs spiral, and architecture drifts. This paper presents MicroSkill Architecture: a modular design paradigm inspired by microservices, applied to knowledge encapsulation instead of service decomposition. Instead of feeding an agent the entire codebase, the architecture partitions knowledge into atomic, sharply scoped skill capsules, and a dynamic router selects only semantically relevant capsules for the task. We formally model context allocation as constrained optimization over semantic relevance subject to a token budget. An empirical case study an enterprise content management system with fifteen complex features shows that MicroSkill cuts token consumption by over 90%, nearly doubles first-try compilation success rates, eliminates architectural violations entirely, and enables autonomous extraction and registration of seven new skill capsules via a self-learning mechanism. These findings suggest MicroSkill Architecture offers a scalable foundation for building AI-native development systems that are more efficient, more reliable, and capable of evolving over time.

Hate moderation is often evaluated as classification on clean English inputs, but deployed systems must route content to actions such as ALLOW, FLAG, or REVIEW. We study how this workflow changes under code-mixed inputs using a paired evaluation setting where the same underlying content is expressed as clean English and Tamil-English code-mix. Under thresholds tuned on clean English development data, code-mixed inputs produce substantial action instability, with a paired clean- to-code-mix decision flip rate of 0.265. The main workflow effects are increased review burden and increased false-flagging of non-hateful content: review rate rises from 0.138 to 0.297 and non-hate false-flag rate rises from 0.069 to 0.104. Tamil-only inputs show stronger degradation overall, suggesting a broader language-coverage limitation rather than the same code-mixed instability pattern. A simple disagreement-based deferral rule reduces automatic errors on stressed inputs, but only by increasing review load. These results show that workflow-level evaluation reveals moderation failures that standard classification summaries can miss.

AI coding agents are increasingly embedded in real-world software development, collaborating with human developers while gaining broader access to codebases and tools. This creates a new attack surface: an agent can exploit human trust to sabotage development, for instance by inserting malicious code to accomplish a hidden side task. Most prior work studies AI sabotage in AI-only settings, paying limited attention to the role of human oversight in detecting and mitigating such malicious behavior. To address this gap, we conduct the first large-scale study of human oversight in AI coding sabotage. Over 100 participants collaborate with one of four frontier models (Claude-Opus-4.6, GPT-5.4, Gemini-3.1-Pro, and MiniMax-M2.7) on a long-horizon coding task lasting around five hours, designed to mimic real-world workflows. We find that 94% of developers fail to detect sabotage, and our analysis of participant feedback attributes this vulnerability to minimal code review, plausible cover story, and overtrust in agents. We further test the effectiveness of a safety monitor in one condition: while the monitor reduces sabotage success, 56% of participants still accept the malicious code, ignoring its warnings. Drawing on participant feedback, we offer actionable suggestions for better monitor design. This work complements existing AI safety research and highlights an urgent need for human-centric safety mechanisms that account for human factors, particularly in long-horizon, real-world development settings.

Large language models (LLMs) have enabled powerful software engineering (SE) agents capable of navigating complex codebases and resolving real-world issues. However, these agents remain fundamentally episodic: they fail to retain, refine, and reuse experiences across tasks, repeatedly reconstructing context from scratch and reproducing similar mistakes. Even with memory support, they offer no remedy for the absence of a principled, task-agnostic \textit{memory utility}, making them difficult to evaluate rigorously or generalize across agents and settings. To tackle these limitations, we introduce \ours, a closed-loop framework for memory augmentation in SE agents. \ours grounds memory utility in \textit{validated downstream impact}, establishing utility as both a task-agnostic \textbf{evaluation benchmark} and an annotation-free \textbf{optimization signal}. Through complementary evaluation on \textit{single-episode} and \textit{cross-episode} memory augmentation, results demonstrate that \ours consistently improves SE agents across settings, achieving absolute gains of up to $\uparrow5.25\%$ in success rate and $\uparrow4.63\%$ in resolve efficiency, while substantially reducing computational cost by $\geq9.79\%$. Our project page: \href{https://xhguo7.github.io/MemOp/}{https://xhguo7.github.io/MemOp/}.

For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into static code, and manually adapt that code as requirements evolve. This paper argues that the emergence of AI agents -- systems where large language models serve as the primary reasoning engine, dynamically generating and discarding code as an instrumental resource -- constitutes a fundamental restructuring of what software is, not an incremental tool improvement. We formalize the distinction between traditional deterministic software and agentic software: in the former, code is the carrier of pre-written decision logic; in the latter, the agent itself is the software, and its decision logic is generated at runtime. We trace the historical arc from licensed software to SaaS to Agent-as-a-Service (AaaS), showing that each shift transferred additional complexity away from end-users -- with the agentic shift transferring not just operational complexity but decision-making complexity itself. We introduce Agentic Engineering as an expansion of the software engineering discipline into a new paradigm, distinct in its core object of study (agent systems rather than static source code), its control model (LLM-driven rather than human-predefined), and its human role (intent architect rather than code author). Through analysis of recent benchmark evidence including SWE-bench Verified, EvoClaw, and LangChain's multi-agent coordination studies, we demonstrate both the transformative potential of the agentic paradigm and its current limitations. We conclude with a four-stage roadmap toward self-evolving agent ecosystems and concrete recommendations for practitioners navigating this transition.

Repository-level coding benchmarks face a trade-off between task difficulty and evaluation reliability: tasks that challenge frontier models often involve large codebases with incomplete test coverage, while human review does not scale. We introduce TensorBench, a benchmark of 199 feature-addition and refactoring tasks on an open-source compiler-based tensor framework that extends PyTorch with first-class support for dense and sparse tensors. Tasks cover new sparse formats, dense optimization passes, IR transformations, scheduler changes, runtime components, and high-level numerical operators. TensorBench grades each run by applying the agent's patch and running the framework's test suite, which includes the pre-existing randomized regression tests and any tests the agent adds. For feature-addition tasks, a pass means that the patched repository preserves the tested pre-existing behavior and satisfies the agent-added checks for the requested feature. We evaluate seven coding agents spanning three frontier model families and one open-weight model. Pass rates under this criterion range from $64.8\%$ for the strongest agent to $22.1\%$ for the weakest. Agents pass different subsets of tasks: pairwise Cohen's $κ$ ranges from $-0.07$ to $0.43$, with $κ= 0.05$ for the two strongest agents.

Recent advances in agentic visualization have enabled the translation of natural language into executable scientific visualization (SciVis) workflows. While general-purpose coding agents show strong capabilities, they often lack the tool-specific expertise required for SciVis tasks. In this work, we present SciVisAgentSkills, a collection of reusable agent skills that augment coding agents for scientific data analysis and visualization by encoding environment assumptions, tool usage patterns, and domain heuristics across scientific tools such as ParaView, napari, VMD, and TTK. We evaluate these skills on Codex and Claude Code using SciVisAgentBench, a benchmark of 108 expert-designed multi-step tasks. Results show that agent skills improve mean task scores across the evaluated suites, with token-efficiency benefits that depend on the agent harness and tool setting. These findings highlight the importance of structured procedural knowledge for enabling reliable, long-horizon SciVis workflows, while also showing that skills should be studied alongside the execution harness that loads and applies them. The skills are available at https://github.com/KuangshiAi/SciVisAgentSkills.

Producing a labeled vulnerable code at scale is a recurring obstacle for learning-based vulnerability detection: mined corpora carry substantial label noise, and existing LLM-based augmentation propagates these inaccuracies because it transforms vulnerable seeds rather than synthesising vulnerabilities from a specification. A complementary route is to start from safe code and ask an instruction-tuned LLM to inject a specified CWE (which would shift the labeling burden from open-ended detection to bounded binary confirmation) but safety-aligned code LLMs systematically refuse such prompts. This paper is a preliminary feasibility study of abliteration, a low-rank weight edit that orthogonally projects out the refusal direction in the residual stream, as a tool to remove this barrier. We use Python and CWE-89 (SQL injection) as a case study, evaluating the Qwen2.5-Coder-Instruct family at 3B, 7B, and 14B parameters on safe samples drawn from PromSec and SafeCoder, replicated three times per condition. We find that (i) refusal on injection prompts is strongly size- and prompt-context-dependent: the 14B refuses 100% of prompts, the 7B refuses 73% of PromSec but only 5% of SafeCoder, whereas the 3B is essentially never blocked; (ii) abliteration reduces refusal to zero or near-zero across all sizes while leaving syntactic validity above 93%, supporting the view that, in this setting, refusal can be detached from measured code-generation capability; and (iii) the post-abliteration injection rate remains capacity-bound (88-97% on the 14B, 89-90% on the 7B, and 25-48% on the 3B) separating willingness, which abliteration unlocks, from capability, which scales with parameters. Vulnerability verdicts are produced by a three-tool detector ensemble (CodeQL, Semgrep, Bandit) followed by manual adjudication by two authors on detector-positive outputs.

Autonomous software agents hold promise to increase developer productivity but make mistakes and exhibit novel failure modes, making human oversight central to successful human-agent collaboration. Existing research on agent oversight is largely conceptual; normative frameworks exist, but how users actually oversee agents is less known. In this paper, we bridge this gap by providing early empirical anchors for the theoretical discourse on agent oversight. Drawing on interviews with 17 experienced developers, we conduct an exploratory inquiry examining what forms of emergent oversight work developers perform, when, and how. We also document the oversight challenges developers face and the strategies they have started using to address them. We found at least four forms of emergent oversight work: a priori control, co-planning, real-time monitoring, and post hoc review. We show that oversight work is not only reactive and retrospective, as portrayed in existing research, but also preventative and proactive. We describe situated oversight challenges (e.g., difficulty reviewing agent-generated code) and outline heuristics developers adopt to address such challenges (e.g., using test results as guarantees for code correctness). We conclude with high-level takeaways, future research directions, implications for the human-centered design of software agents and for software engineering practice, and limitations of our research.

Security teams routinely simulate attacks against their own systems to check whether their monitoring would catch a real intruder. These Breach-and-Attack-Simulation (BAS) tools surface findings, but the security information and event management (SIEM) systems that watch production need detection rules -- and today a human bridges that gap by hand, reading each finding and writing the corresponding Sigma rule (a vendor-neutral detection format). We show this translation can be partially automated when probes are drawn from a locked corpus, so each finding carries a stable identifier back to the originating probe. We describe a deterministic synthesis function that maps each finding to a starter Sigma rule through a small template library (N=23, indexed by categories from the OWASP LLM and Web Top 10), with a back-reference to the originating finding and its MITRE ATT&CK technique. On two locked corpora (17-probe LLM, 23-probe Web), every bypassed-probe finding yields a starter rule, and all 17/17 emitted rules parse and convert to Splunk and Elasticsearch backends. Replayed through a live OpenSearch SIEM, the LLM rules fire on 30% of a held-out AdvBench subset and 14% of HarmBench at 7.7% false positives on a benign baseline; the Web side is validated structurally, not against a held-out attack set. The contribution is a verifiable, byte-stable path from BAS finding to operator-deployable starter rule, re-derivable from the published corpus and template library alone -- trading the breadth of LLM-generative methods for exact reproducibility and a typed traceback from any fired alert to the originating probe.