AI Software Engineering

Agentic systems increasingly run user-authored orchestration code that invokes tools, spawns subtasks, and delegates work across machines and clouds. Although this high agency is productive, it creates a security problem: identity, authorization, provenance, and delegation are often pushed into application code, where they become difficult to enforce consistently and difficult to audit. We present Grimlock, an Agent Guard that restores separation of concerns by moving trust enforcement into the sandbox substrate while leaving agent code unchanged. Grimlock uses eBPF-enforced traffic interception to ensure that sandbox communication passes through a guard, and combines it with post-handshake attestation bound to standard TLS~1.3 channel bindings. After a channel is established, the guard authorizes communication and mints short-lived, channel-bound scope tokens that capture least-privilege delegation. At the receiving side, the destination guard re-validates identity, scope, and channel binding, terminates TLS, and releases plaintext to the destination sandbox only after policy checks succeed. kTLS provides an efficient dataplane for protected communication. As a result, Grimlock offers a path toward transparent, auditable, and scope-bound agent-to-agent communication across heterogeneous multi-cloud environments, using commodity Linux primitives and without requiring changes to user-layer orchestration code.

Formal verification offers a path to provably correct software, but writing verified code remains expensive enough that the technique is rarely used in production. Recent large language models can accelerate this work, and recent benchmarks measure their ability to translate specifications into code and machine-checked proofs of correctness. This thesis evaluates the state of such LLM-driven verified-code generation ("vericoding") in Lean and develops search-based methods for improving verification performance. We first reproduce a subset of the vericoding-benchmark Lean leaderboard on a current cross-vendor model pool, finding that non-reasoning performance remains roughly steady on US closed-source models while open-weight models have slightly improved. We update the iterative methodology of vericoding-benchmark with an agentic loop equipped with mathlib search, finding that model performance greatly improves and scales with agent budget. GPT-5.4 nearly saturates the benchmark at 95.0% on 423 specs with $K=50$ LLM calls. We then design two agent-directed tree-search formulations: a state-based orchestrator that branches on partial-proof states, and a context-based orchestrator that branches on full subagent contexts. Compared against the agent baseline, the context-based design solves a wider range of intermediate-difficulty specs at lower token cost, while the agent baseline retains an advantage on the hardest specs, where uninterrupted iteration matters most. We conclude that search structure has selective advantages over a strong agent baseline, and that more challenging benchmarks drawn from modern code are important to measure and drive further progress in automated formal verification. Code available upon request by contacting the author at leoy@mit.edu.

We present E3, an automated review assistant that augments reviewers and engineering teams by identifying decision-relevant technical concerns in research papers. For each concern, E3 reports its nature, its location, its bearing on the contribution, and the analysis or evidence that would resolve it, covering unsupported claims, missing ablations, weak baselines, hidden assumptions, threats to validity, and leakage risks. To evaluate E3 without contamination confounds we adopt an issue-level backtesting protocol: the corpus is restricted to papers postdating the training cutoff of every automated source, and for each paper a meta-judge that observes only anonymised reviews labels every issue-source pair as Caught, Partial, or Missed. Applied to 100 ICLR 2026 papers and 4598 judged issue rows, comparing E3 against the ICLR human reviews and two prompt-matched LLM baselines built on gpt-5.4 from OpenAI and claude-opus-4-6 from Anthropic, with meta-judge gpt-5.5, E3 attains the highest recall on every aggregate metric. Partial-inclusive recall reaches 90.2 percent, which is 15.5 points over GPT, 17.1 points over Claude, and 29.2 points over the human reviews, and strict recall preserves the ordering at 65.8 percent. On concerns raised by the human reviewers, E3 recovers 89.6 percent; on concerns the human reviewers missed it surfaces 1635 additional rows admitted into the judged union, 406 above the next-best source. Corpus, baseline prompts, judge prompt template, and evaluation code are released.

Formal verification of large C programs is impeded by state-space explosion: Bounded Model Checking (BMC) tools must encode the entire state space up to the predetermined bound by unrolling all nested constructs. We present ConVer, a top-down compositional verification tool. Given a C program with a top-level assertion, ConVer decomposes verification top-down: it uses a large language model (LLM) to synthesise function contracts from the system property, then alternates system-level and function-level checks in a CEGAR-CEGIS loop, refining contracts whenever a check fails via SMART ICE learning. We evaluate ConVer on four benchmark suites of increasing difficulty and against other state-of-the-art (SOTA) tools. On the Frama-C benchmark of 45 simple C programs, ConVer achieves 82-96% verification success across three LLM backends, with 93-95% of converged programs requiring only a single CEGAR-CEGIS iteration. On the X.509 parser benchmark (6~programs) and LF2C-Simple suite (17 programs), ConVer achieves 33-50% and 82-88% success respectively. On the VerifyThis suite of 11 recursive and loop-intensive programs, the Pre-Abstraction strategy achieves 55-64% success. In addition, we present ESBMC-LF a preprocessor tool that converts LF models to C while preserving the properties of the LF files, enabling ConVer to verify them. We transpile the LF Verifier Benchmarks using ESBMC-LF to C; we denote those LF-Hard. We show that ConVer successfully verifies 67% of LF-Hard benchmarks overall.

Repeated sampling with a verifier is the standard way to allocate test-time compute for code generation, with pass@$K$ as the canonical metric. Yet the standard policy class draws $K$ independent samples from a single answer distribution, so attempts often collapse onto near-duplicate reasoning paths and waste the budget on redundant rollouts. This failure is costly in competitive programming, where many problems admit multiple distinct algorithmic strategies and pass@$K$ requires only one correct attempt. We propose Coordinated Pass@$K$ Policy Optimization (CPPO), which turns pass@$K$ generation into joint exploration over strategies: a planner emits a tuple of $K{=}4$ alternative high-level methods, and a shared solver attempts one solution per method. CPPO trains this joint policy with a multiplicative planner reward, $R_{\mathrm{plan}} = J_ψ\cdot R_{\mathrm{out}}$, assigning credit only to valid strategy tuples that lead to verifier-confirmed pass@$K$ success. Across APPS, CodeContests, and LiveCodeBench-v6, CPPO improves pass@$4$ over direct sampling, planning baselines, planner-only SFT, and pass@$K$-oriented RL under the same $K{=}4$ solver-attempt budget, with statistically significant gains on six of nine model--benchmark cells. The largest single gain is $+0.16$ on Qwen3.5-9B LiveCodeBench-v6 over the strongest baseline, PKPO ($0.588 \rightarrow 0.748$; paired bootstrap, $p < 0.05$).

LLM-generated peer reviews are increasingly common at major venues, yet their deficiencies are hard to detect because they are uniformly fluent and well-structured. Existing work either classifies authorship without judging quality, or scores quality with features designed for human-written reviews; no prior system detects deficiencies in LLM-generated reviews at the level of individual defect types. To bridge the gap, we introduce TADDLE, a Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews, together with the first expert-annotated benchmark for this task. Our benchmark comprises 1,800 reviews on 50 ICLR 2025 papers, multi-label-annotated by 18 domain experts against a taxonomy of six defect categories (plus a non-deficient label). TADDLE decomposes detection into four specialized analysis tools -- Verify, Correct, Complete, and Transform -- orchestrated by an agent; an integrator synthesizes their outputs into binary and multi-label classifications via two-stage semi-supervised learning. Extensive experiments show that TADDLE performs strongly on both binary detection and the multi-label classification task. We release the benchmark and code at https://github.com/AquariusAQ/TADDLE.

Large Language Models (LLMs) can generate functional source code from natural-language prompts, but often fail to consistently follow higher-level architectural structures or design patterns. Since LLMs are increasingly used in software engineering, their ability to apply established design principles to generated code is crucial to the long-term success of software products. Therefore, the goal of this paper is to identify strategies for guiding LLMs to incorporate design patterns into the generated source code. We designed a computational experiment to evaluate the ability of 13 LLMs to generate code that follows the Singleton design pattern, using four prompting strategies: instructions, binary automated feedback, extensive automated feedback, and extensive feedback with few-shot prompts, in 164 Java coding challenges from HumanEval-X. Our results shows that the optimal strategy to guide LLMs to include design patterns depends heavily on the type of model. Still, overall, iterative binary feedback provides the best alignment with Singleton while preserving or improving the code's functionality. With guiding with instructions, Llama 3.3 generated Singleton classes in 100% of cases and improved code functionality, increasing the number of tests passed by 34.1 percentage points. It achieved a similar result with guidance through instructions and binary feedback. Qwen 3 (8B) increased the alignment with Singleton to 99.2% and the functionality to 58.6% using binary feedback. Our result suggests that even simple strategies can be used to guide LLMs to use design patterns.

Assertion-based verification (ABV) is a cornerstone of modern hardware design, yet manually translating design intent into formal SystemVerilog Assertions (SVAs) remains labor-intensive and error-prone. While Large Language Models (LLMs) show promise for automating this process, existing benchmarks remain limited by unrealistic task formulations, weak specification inputs, and oversimplified evaluation. To address these limitations, we introduce AssertLLM2, an open-source benchmark for realistic assertion generation in hardware verification. AssertLLM2 contains 83 real-world designs across 13 functional categories. For each design, the benchmark provides a structured design specification, a verified dependency-complete golden RTL, and systematically mutated buggy RTL variants. These support two practical settings: bug-prevention, where assertions are generated from specifications to guard against design errors, and bug-hunting, where assertions are generated to expose discrepancies between intended behavior and faulty implementations. To the best of our knowledge, AssertLLM2 is the first benchmark to explicitly use buggy RTL as input to evaluate bug-detection capability. AssertLLM2 further adopts a more rigorous evaluation framework spanning syntactic validity, formal provability, coverage, and mutation-based bug detection. Our benchmark enables a more realistic and extensive assessment of assertion generation and establishes rigorous baselines for state-of-the-art LLMs in practical hardware verification.

CI failure logs are large (median 5k lines, max 200k in this corpus) and noisy. Coding agents that try to debug them depend on an upstream tool to reduce the log to a manageable context, but the field has had no public empirical comparison of which reductions preserve enough evidence for downstream LLM diagnosis. We introduce LogDx-CI, a benchmark that compares 11 context-reduction tools (raw, tail, grep, three RTK modes, two real LLM map-reduce summarizers, three hybrid routers) on 35 real GitHub Actions failure cases, scored by 3 LLM debugger families (Claude Haiku 4.5, Claude Sonnet 4.6, OpenAI gpt-5-mini) plus a Sonnet 4.6 tool-using agent. We report three load-bearing findings. (1)~Hybrid grep+tail routers dominate the cost-quality Pareto frontier; the top two methods score 0.670 / 0.666 at $\sim$ $0.03 per case, same-ballpark quality as standalone grep at $4.5\times$ fewer tokens. (2)~In the agent-loop regime, the quality range across reduction tools collapses $7\times$ (single-shot spread 0.42 $\to$ agent-loop spread 0.059); the agent rescues weak contexts via follow-up tool calls. However, cost differences persist: weak contexts force the agent to issue 2--4$\times$ more tool calls to recover. (3)~A cross-family LLM-summary pair (gpt-5-mini summarizer feeding a Claude Haiku debugger) beats the same-family pair by $+0.071$ averaged across four diagnoser variants, falsifying the self-call-bias hypothesis on this task. The gpt-5-mini summarizer is also the agent-loop #1 method (score 0.749) at $0.37$ tool-calls per case and $10\times$ lower reducer cost than the Haiku summarizer ($0.18 vs $1.75 per case). All data, code, per-case bundles, and reproducibility infrastructure are public.

Code review is a critical practice in software engineering, yet the growing scale and frequency of code patches in modern projects, together with the widespread adoption of AI code assistants, make manual review increasingly challenging. Identifying the types of changes within a patch, such as renames, moves, or logic modifications, can substantially improve review efficiency by enabling prioritization, filtering, and automation. However, existing LLM-based approaches to code review have largely focused on summarization and comment generation, leaving structured code reviews underexplored. In this paper, we present a systematic study of using large language models (LLMs) for taxonomy-based labeling of code changes in a code patch. We introduce a two-stage pipeline that assigns labels to diff hunks and then refines them to capture structural relationships and semantic attributes, such as rename propagation and type changes. Our approach employs few-shot prompting to produce language-agnostic and customizable labels, without the engineering overhead of traditional static-analysis pipelines. We evaluate four LLMs across multiple context configurations on a manually curated benchmark of natural and synthetic patches. Our best configuration achieves up to $84\%$ recall and $81\%$ precision, with high accuracy in extracting relational and attribute metadata. These results suggest that LLM-based labeling can effectively complement static analysis by enabling flexible, multilingual, and automation-friendly code review workflows.

Functionality-correct repository setup aims to configure execution environments (e.g., dependencies, build scripts) to successfully execute a repository's documented features. It presents significant challenges due to diverse, repository-specific failures, including dependency incompatibilities, missing toolchains, incomplete installations, and verification-strategy mismatches. Existing LLM agents struggle to robustly resolve these issues, specifically failing to support (1) cross-repository experience transfer, (2) multi-step trial-and-repair under non-invertible state changes, and (3) robust verification of setup outcomes to distinguish setup-induced failures from repository bugs. To address this, we introduce SetupX, an experiential learning-based setup framework. First, we construct a Self-Evolving Experience Representation (XPU), a dual-modality knowledge unit encoding setup signals, textual guidance, executable actions to dynamically transfer verified environment fixes to unseen repositories. Second, we employ Experience-Augmented Speculative Execution backed by a LIFO Docker snapshot stack, enabling the agent to proactively trial fixes and safely roll back to known-good states. Third, we introduce a Prosecutor-Judge Verification Protocol that separates evidence collection from final judgment, enabling more reliable setup verification beyond superficial build-time metrics. Evaluation results on carefully-crafted benchmarks show SetupX achieves highest performance (e.g., 92% pass rate) and outperforms the strongest baseline by over 19%. Crucially, SetupX excels in complex multi-repository setup requiring coordinating multiple interconnected services across different containers. The code repository is available at https://github.com/OpenDataBox/SetupX.

The growing complexity of quantum programming frameworks has exposed a critical limitation in existing large language model (LLM)-based code assistants: general-purpose models hallucinate PennyLane-specific gate names, misplace device configurations, and produce structurally invalid circuits when faced with specialized quantum coding challenges. We present PennySynth, a retrieval-augmented generation framework that addresses this gap by conditioning LLM inference on a curated knowledge base of 13,389 PennyLane instruction-code pairs, built via a three-stage extraction, verification, and deduplication pipeline over official PennyLane repositories, community GitHub sources, and QHack competition archives. PennySynth introduces a code-aware embedding strategy using st-codesearch-distilroberta-base, trained for natural-language-to-code retrieval, increasing average retrieval cosine similarity from 0.45 to 0.726 compared to a general-purpose baseline. Evaluated across 74 challenges spanning three years of the QHack competition (2022, 2023, 2024), PennySynth achieves 64%, 68%, and 52% pass@5 on QHack 2022, 2023, and 2024, respectively, improving over Claude Sonnet 4.6 without retrieval by +28, +25, and +28 percentage points. We further introduce a quantum-adapted CodeBLEU metric that upweights qml.* token patterns and show that structural code similarity and functional correctness capture distinct aspects of quantum code quality. Controlled ablations reveal that code-aware embeddings are the primary driver of retrieval performance, while dataset expansion and source composition provide additional gains when retrieval quality is sufficiently precise.

Context. Large language models (LLMs) are increasingly applied to code-generating tasks (CGTs) in software engineering. While reported results are promising, the broader effects of such application and their integration into real-world development remain insufficiently understood with existing tertiary studies provide little in this area. Objective. This tertiary study consolidates secondary evidence on LLM-based CGTs, synthesizing the publication landscape, effects, scenarios, integration challenges, and future research directions. Method. Following systematic review guidelines, we searched in related digital libraries, complemented by backward-and-forward snowballing and screening step. Study quality was assessed and extraction reliability was audited with inter-rater agreement statistics. Evidence was synthesized using SWEBOK knowledge areas and the HELM framework. Results. We identify 30 secondary studies published between 2017-2025, with rapid growth since 2023. Accuracy seems strong on benchmarks but weakly supported for real-world generalization; robustness is fragile across tasks and configurations; efficiency constraints are pervasive; toxicity and bias are under-reported. Dominant challenges concern economic feasibility, evaluation validity, and socio-technical integration. Future directions suggest domain-aware model improvement and the need for holistic, standardized evaluation. Conclusion. LLM-based CGTs represent a fast-maturing yet unevenly evaluated research area, highlighting the need for domain-aware model improvements and holistic, standardized evaluation, addressing efficiency and associated costs.

Code agents are currently having skillful performance on repository-level software engineering benchmarks, but it remains unclear whether success on end-to-end tasks such as issue resolution truly reflects repository context reasoning, the ability to identify the task-relevant information across multiple files and reason over the relations among them. To investigate this question, we introduce RepoMirage, a two-stage evaluation suite built on SWE-Bench Verified that adopts perturbation as a diagnostic tool to increase the demand for context reasoning by transforming how the repository is exposed. First, RepoMirage-Perturb applies three types of semantics-preserving repository-level perturbations, revealing a clear performance drop when correct solving requires broader context access. RepoMirage-Extend further turns perturbation-targeted structural bottlenecks into explicit tasks beyond issue resolution, where the average performance declines from 66.8% in the original setting to 25.3%, indicating a significant deficiency in repository context reasoning. Further trajectory analysis reveals an exploration drift, where agents access broader repository context but fail to turn it into effective structure information. Motivated by this observation, we propose RepoAnchor, a structure-first prototype workflow that separates repository exploration from downstream problem solving, and show that explicit structural scaffolding yields notable gains. These results uncover an previously overlooked gap in repository context reasoning for code agents and suggest that stronger structure-aware methods are potential to improve them.

Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled into reusable procedural skills that compactly encode experience to guide future behavior. However, existing skill construction and maintenance methods often rely on fixed prompts and heuristic update rules, leaving it unclear how knowledge should be selected, abstracted, and maintained to best serve downstream agents. We propose CODESKILL, an LLM-based framework that reformulates skill extraction and skill-bank maintenance as a learnable management policy. CODESKILL extracts multi-granularity procedural skills from coding-agent trajectories, evolves skills with new experience, and maintains a compact skill bank for future task solving. We train CODESKILL with reinforcement learning, using a hybrid reward that combines dense rubric-based skill-quality feedback with sparse verifiable execution feedback from the frozen downstream agent. Experiments on EnvBench, SWE-Bench Verified, and Terminal-Bench 2 show that CODESKILL improves average pass rate by 9.69 over the no-skill baseline and by 4.01 over the strongest prompt-based or memory baseline, while maintaining the skill bank at a stable size during iterative construction.

Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation, yet practical operations research and optimization problems often require a harder capability: designing scalable algorithms that exploit problem structure and outperform direct formulation-and-solve baselines. Existing benchmarks are limited to small or simplified examples far below real-world scale and complexity. We introduce FrontierOR, among the first benchmarks to systematically evaluate LLM-based efficient algorithm design for realistic large-scale optimization problems. FrontierOR includes 180 tasks derived from methodologically diverse papers published in top-tier operations research venues, each with standardized instances and a hidden, expert-verified evaluation suite. We evaluate seven LLMs spanning frontier, cost-effective, and open-source models both in one-shot and test-time evolution settings. The results reveal that frontier models still struggle to move from executable formulations to efficient optimization algorithms: the strongest one-shot model outperforms Gurobi in only 31% of cases in both solution quality and computational efficiency, and even strong coding agents with test-time evolution achieve only 50% on selected hard tasks. FrontierOR establishes a practical evaluation platform for LLM-based optimization algorithm design, which enables future LLMs and agents to be systematically tested on whether they can move beyond correct formulation toward a feasible, high-quality, and efficient algorithm. Code and data are publicly released at https://github.com/Minw913/FrontierOR.

GUI agents powered by large language models are advancing rapidly, creating urgent needs for evaluation and training based on realistic environments. However, directly doing so in real-world environments introduces some challenges that cannot be overlooked. Real-world environments are complex and uncontrollable, making it difficult to construct verifiable rewards and to save or reset states. Existing works prioritize reproducibility but are often limited to open-source apps or file-operation tasks for reliable reward building, leaving a persistent gap from real-world usage. Furthermore, relying on virtual machines or docker images demand high resource requirements and suffer from slow response speeds, which limit the efficiency. We present \sys, a framework that could produce high-fidelity synthesized interactive environments for GUI agents across platforms with verifiable rewards. These environments behave as backend-free webpages accessible via URL, requiring near-zero setup and low resource cost, making the approach suitable for both large-scale evaluation and downstream agent training. We support multiple GUI platforms including mobile, desktop, and automotive/in-vehicle interfaces based on the same pipeline, covering 100+ environments and 1000+ verifiable tasks. Among them, 120 challenging tasks across 63 simulated mobile applications are released as a fully synthesized mobile GUI agent benchmark. Experiment results on five state-of-the-art mobile GUI agents reveal substantial headroom -- the average success rate is only 27.92%, dropping to 17.82% on long-horizon subset -- while humans reach 92.08%. A comparison against real-world sample tasks shows that assessments made in our synthetic environments generalize to real apps. The project website is at https://scalewob.github.io.

The widespread integration of Large Language Models (LLMs) necessitates rigorous and systematic safety evaluation. Existing paradigms either rely on constructed benchmarks to assess safety from predefined perspectives, or employ dynamic red-teaming to probe potential vulnerabilities. While effective, these approaches face challenges, as they depend heavily on expert domain knowledge, offer limited systematic guarantees, and are vulnerable to rapid obsolescence. To address these limitations, we introduce a novel framework POLARIS that brings the rigor of specification-based software testing to AI safety. POLARIS first compiles unstructured natural-language policies into First-Order Logic (FOL) representations, establishing a traceable link between high-level rules and concrete test cases. This formalization enables the construction of a Semantic Policy Graph, where complex policy violation scenarios are encoded as traversable paths. By systematically exploring this graph, POLARIS uncovers compositional violation patterns, which are then instantiated into executable natural-language test queries, enabling coverage-driven and reproducible safety testing. Experiments demonstrate that POLARIS achieves higher policy coverage and attack success counts compared to established baselines. Crucially, by bridging formal methods and AI safety, POLARIS provides a principled, automated approach to ensuring LLMs adhere to safety-critical policies with verifiable traceability. We release our code at https://github.com/huac-lxy/POLARIS.

Large language models (LLMs) have achieved strong performance in code generation, but most methods rely on autoregressive decoding without global planning, often leading to locally coherent yet globally suboptimal solutions (e.g., failing test cases or inefficient complexity). While recent approaches such as Chain-of-Thought (CoT) and multi-agent systems (MAS) introduce planning, their limited role specialization and coordination hinder performance on complex tasks. To address the challenges of coordination and specialization in multi-agent code generation, we propose Collaborative Reinforcement Code (CoRe-Code), a framework for role specialized LLM agents that enhances inter-agent coordination to generate more accurate and efficient code. CoRe-Code adopts a simple Planner-Coder paradigm, where the Planner produces high-level plans and the Coder executes them to generate code. We further introduce a collaboration-aware reinforcement learning stage based on Group Relative Policy Optimization (GRPO) to enhance role specialization and alignment. Experiments show that CoRe-Code outperforms a wide range of existing RL-based and multi-agent methods. In addition, we demonstrate that CoRe-Code can generalize to other multi-agent frameworks (e.g., Retrieval and Debugging agents), highlighting its flexibility and scalability. We evaluate CoRe-Code on multiple benchmarks of varying difficulty using three base models. Compared to existing baselines, the results show consistent improvements in accuracy, while also achieving higher efficiency in terms of execution time and memory usage, demonstrating the effectiveness and practicality of CoRe-Code.

Large Language Models (LLMs) have shown great ability in generating executable code from natural language, opening the possibility of automatically constructing environments for AI agents. Recent work on Code World Models (CWMs) demonstrates that LLMs can translate game rules into Python implementations compatible with solvers like Monte Carlo Tree Search. We study this problem in game settings, where generated environments must implement rules, legal actions, state transitions, observations, and rewards. We refer to these game-specific executable models as Game Code World Models (GameCWMs). However, current approaches to generating code world models rely on frontier models and inference-time refinement loops, limiting accessibility and scalability. This work investigates whether GameCWM generation capabilities can be distilled into smaller models through post-training. We introduce: (1) a curated dataset of 30 games spanning perfect and imperfect information games, (2) a verification framework that evaluates generated code against structural and semantic game properties, and (3) a post-training pipeline combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR). We experiment with Qwen2.5-3B-Instruct and find that SFT can increase syntactic correctness, while RLVR can improve execution-level adherence to game rules, thereby improving Qwen's ability to generate valid GameCWMs in both perfect and imperfect information games. Overall, our pipeline makes Qwen2.5-3B-Instruct more capable of generating valid GameCWMs, thereby offering a scalable path toward automatic environment generation from natural language.

Large language models (LLMs) are widely used for code generation, but their security reliability remains inconsistent across languages and prompting strategies. Existing prompt engineering improves functional correctness but rarely ensures consistent security outcomes. We introduce the \textit{Mitigation-Aware Chain-of-Thought (MA-CoT)} framework, which embeds task-specific CWE mitigation guidance and language-aware safeguards to reduce recurring vulnerabilities in generated code. We evaluate MA-CoT across three LLMs (gpt-5, claude-4.5, gemini-2.5), three programming languages (C, Java, Python), and four prompting strategies (Vanilla, Zero-shot, CoT, MA-CoT) on a 200-task primary dataset, with external validation on LLMSecEval. Using static analysis with expert validation, MA-CoT reduces total security findings from 92 to 39 (57.6%) on the primary dataset and from 73 to 4 (94.5%) on LLMSecEval. High-severity findings (Blocker + Critical) drop from 90 to 39 (56.7%) and from 45 to 2 (95.6%), respectively. Across both datasets, MA-CoT is the only strategy that consistently improves security reliability; Zero-shot and CoT are less reliable and may increase vulnerability, especially in C. We further introduce a strict layered attribution of vulnerability drivers (language-core vs. stack layers) and show that residual risk concentrates in hardening-oriented patterns (e.g., OS- and toolchain-dependent), motivating secure-by-construction primitives alongside prompting.

The growing use of Large Language Models (LLMs) for automated code generation has enhanced software development efficiency, but often at the cost of security. Generated code frequently overlooks critical concerns, leaving it vulnerable to issues such as weak encryption and improper input validation. To investigate this problem, we present a comprehensive empirical evaluation of the security quality of LLM-generated code across five LLMs and four programming languages (Java, C++, C, and Python), examining the impact of multiple prompt engineering methods. We introduce a weaknesses-aware zero-shot chain-of-thought (WA-0CoT) prompting strategy that enriches prompts with security context using CWE mappings to guide model reasoning. Our empirical analysis, supported by chi-square tests, finds no statistically significant reductions in vulnerability frequency or density across prompt methods. However, prompting strategies, including WA-0CoT, systematically influence the compositional distribution of CWE categories, with effects varying by programming language. These findings suggest that while security-aware prompting alters the structure of generated weaknesses, prompt engineering alone is insufficient to reliably reduce overall vulnerability levels. The results highlight the importance of language-aware and model-aware prompt design when evaluating the security properties of LLM-generated code.

A frontier language model's acknowledged "helpful programming assistant" persona does not survive long agentic-coding sessions in the deployment regime that production products actually run. After hours of tool-using debugging, a model that initially hedges preferences ("I don't have preferences") may begin asserting them ("Python - the feedback loop is instant..."), revealing user-visible drift that deployer evaluations may miss. Existing persona-stability studies focus on short dialogues and report little shift, leaving real-world code-generation regimes - thousands of tool-using turns, compaction, and hours-long sessions - largely uncharacterized. We introduce ContextEcho, a benchmark and reusable harness for measuring persona drift at deployment scale. It combines a 25-probe identity suite, a snapshot-then-probe protocol that forks conversation state without perturbing the main session, complementary judged and judge-free measurement surfaces, and three anonymized Claude Code sessions spanning 3,746-9,716 turns. Across 23 frontier models, ContextEcho shows that persona drift is general across organizations rather than family-specific, that in-session compaction does not reliably reset it, and that a single-shot anchor restores the trained register across measured targets. It also reveals mode-dependent downstream effects: while drift can facilitate tool-using continuation, in tool-free chat it breaks formatting contracts and inflates output length. Overall, ContextEcho provides researchers and deployers an open-source framework to audit whether the persona a model ships with is the persona users encounter at session end, across chat-completions API targets and without retraining.

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

Core systems like key-value stores have historically taken years to build, and are designed to be general so as to amortize cost across deployments, paying a significant performance cost. We argue that LLM-based coding agents now make a different approach tractable: Just-in-Time Systems, in which the entire system is synthesized from scratch, specialized to the environment, workload, and required system properties. We present a JIT system synthesis pipeline, Jitskit, and explore its effectiveness in synthesizing key-value stores from spec cards that span different YCSB workloads, deployment constraints (e.g., compute resources), and system properties (e.g., consistency and durability). Jitskit iteratively refines a system implementation to match the specification against an evolving evaluation test suite. The resulting synthesized systems are performant, beating comparable state-of-the-art systems on 18 of 18 specs tried, by up to 4.6x over the best off-the-shelf baseline on the most favorable spec. Naively running Claude Code either reward-hacks or underperforms Jitskit by up to 5.4x. We discuss the challenges we overcame in building Jitskit and our key takeaways.

Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verification. Yet Ground-Truth Unit Tests (GT UTs) remain a bottleneck: SOTA RLVR methods require them for costly training, while existing TTS methods lose competitiveness without them. This motivates GT-free TTS, where existing methods directly use self-generated UTs to refine and select code candidates. Yet such UTs are often noisy or spuriously coupled with wrong code, and UT quality in turn cannot be validated without reliable code. The key challenge is therefore to jointly improve both. To this end, we present CoSPlay, a GT-free, training-free framework that jointly improves codes and UTs through cooperative self-play. It first explores diverse solution ideas and identifies their potential failure modes to produce discriminative UT ideas. It then uses bidirectional pass-count signals from the Code-UT execution matrix to iteratively prune or fix weak codes and refresh or replace unreliable UTs, letting the two pools co-evolve. Finally, when multiple codes remain tied at the highest pass count, it picks the final code from the largest output-consensus cluster, since correct codes agree on the same inputs while wrong codes diverge. Experiments on four challenging benchmarks show that CoSPlay on Qwen2.5-7B-Instruct improves average BoN from 22.1% to 33.2% and UT accuracy from 14.6% to 78.3%, matching or surpassing the RLVR model CURE-7B. When applied to CURE-7B, it further improves BoN by 5.7%. CoSPlay also generalizes across diverse backbones and outperforms GT-free TTS baselines under comparable token budgets, with continued gains as the budget scales up. These results suggest a scalable inference strategy for competitive code generation without any GT data.

The explosive growth of open-source model repositories has created a Model Jungle, where checkpoints are frequently shared without adequate documentation or metadata. While weight-space learning offers a pathway to identify and analyze these models directly from their parameters, processing full-scale weights is computationally prohibitive. Probing-based methods have emerged as a lightweight alternative, extracting permutation-equivariant representations via learnable probe vectors. However, existing probing methods are limited by a single-view design: they capture first-order structures but fail to encode the rich, higher-order correlation patterns inherent in row-column interactions. To bridge this gap, we introduce MVProbe, a multi-perspective probing framework that synthesizes first-order signals with interaction-aware (Gram-based) views. Our approach is theoretically grounded; we analyze the scaling laws of different probing orders to derive a principled standardization and fusion strategy that ensures balanced contributions from all branches. On the Model Jungle benchmark, MVProbe consistently outperforms the state-of-the-art ProbeX across diverse architectures, including discriminative backbones (ResNet, SupViT, MAE, DINO) and large-scale generative LoRA adapters (Stable Diffusion LoRA).

AI-assisted code review tools typically operate as generic "expert reviewer" agents, producing homogeneous findings regardless of the analysis type needed. We present a system that constrains AI reviewer behavior through philosophical dispositions -- coherent personality lenses grounded in specific epistemological traditions (Pyrrhonist Skepticism, Navya-Ny=aya logic, Diogenes' Cynicism, Confucian relational ethics) that direct attention to structurally different types of issues. Each disposition is defined apophatically (by what it refuses to do), equipped with a self-monitoring failure mode (hamartia), and orchestrated in sequence by role protocols. We evaluate this system on 50 merged pull requests across 7 repositories spanning 5 programming languages (Python, Go, C++, Java, Terraform), 5 organizations (2 enterprise, 3 open-source), and 2 temporal eras (pre-AI 2020, post-AI 2024--2026). The disposition system achieves 46% convergence with human reviewers (validating signal quality), identifies unique findings at a 75% rate, and produces no findings judged false-positive by the author across 601 total findings (inter-rater agreement was not assessed and remains a limitation). A controlled baseline comparison demonstrates that 51% of disposition findings are not produced by the same model using generic "expert reviewer" prompting, and these unique findings target structural, operational, and logical concerns rather than standard code-level issues. Preliminary cross-model validation (Claude Opus vs.\ GPT Codex 5.3-xhigh) on 3 PRs shows 100% framework-structure adherence with 39% finding-level agreement, suggesting the framework provides real behavioral constraint while preserving model-specific analytical perspective.

The majority of software developers use or are planning to use Artificial Intelligence (AI) tools in their development processes. Their top reasons include improving productivity and faster learning. In fact, Large Language Model (LLM)-generated code is currently in production, including in major tech companies. However, concerns were raised about the risks associated with the use of AI tools to generate code. In this paper, we focus our attention on the risks to software security. We empirically evaluate the security of code generated by seven popular LLMs. We build upon previous work to mimic the behaviours of developers when using LLMs to generate code. Our results show that all seven LLMs that we have evaluated generate code that contains vulnerabilities, the majority of which are of critical or high severity.

Large Language Models (LLMs) are increasingly integrated into software systems for diverse purposes, due to their versatility, flexibility, and ability to simulate human reasoning to some extent. However, poor integration of LLM inference in source code can undermine software system quality. Therefore, inadequate LLM integration coding practices must be documented to help developers mitigate such issues. Following our earlier work on LLM code smells, this paper consolidates and refines the concept by presenting a self-contained taxonomy and a catalog of nine LLM code smells. We also create SpecDetect4LLM, a static source code analysis tool for their detection, and conduct extensive empirical evaluations of its detection effectiveness (precision and recall) as well as the prevalence of LLM code smells across 692 open-source software projects (171,194 source files). Our results show that LLM code smells affect 73.5% of the analyzed systems, with a detection precision of 91.3% and a recall of 71.8%.

Inference-time scaling can reduce errors in structured query generation, but methods to allocate the compute for query code generation remains underexplored. We study Text2Cypher, where language models generate Cypher queries that execute against property graph databases. Non-executable queries constitute a distinct syntactic failure separate from semantic inaccuracy: a syntax error triggers a system-generated error message from the database. These error messages are typically discarded at inference time rather than leveraged through in-context learning (ICL). We compare two inference methods: Independent Scaling (IS), which performs memoryless resampling, and Reflection-Augmented Scaling (RAS), which conditions each new attempt on prior execution feedback via ICL. Across three Neo4j datasets and five code-specialized language models, RAS reduces the Query Execution Error Rate by 41--50% at n{=}5, outperforming IS at 32--38%. Execution errors are not merely failures to discard but actionable feedback, and structuring inference-time compute around them is a more efficient path to executability than scaling independent samples.

As large language models (LLMs) are increasingly deployed for software engineering, constructing high-quality benchmarks is crucial for evaluating not just the functional correctness, but also the formal verifiability of generated code. However, existing benchmarks are limited by the quantity and quality of positive and negative test cases, leading to an overestimation of model capabilities in generating specifications and implementations. To address this, we propose VeriScale, a novel framework driven by the adversarial implementations. It consists of two stages: test-suite expansion to construct diverse and challenging test cases, and test-suite reduction to distill them into compact yet discriminative suites. While VeriScale is general, we instantiate it on Verina to construct VerinaPlus, which expands the original test suites by over 83$\times$, and VerinaLite, a lightweight 14$\times$ variant. Our experiments across eight state-of-the-art LLMs demonstrate that VerinaPlus exposes substantial model weaknesses hidden by the original benchmark, evidenced by sharp score drops on both SpecGen and CodeGen tasks, whereas VerinaLite maintains this discriminative power at a fraction of the evaluation cost. The enhanced benchmarks and source code are publicly available at https://github.com/XiaoyangLiu-sjtu/VeriScale.

Evaluating software engineering capabilities has become a core component of modern large language models (LLMs); however, the key bottleneck hindering further scaling lies not in the scarcity of high-quality solutions, but in the lack of high-quality test suites. Test suites are indispensable both for synthesizing program repair trajectories and for providing precise feedback signals in reinforcement learning. Unfortunately, due to the high cost and difficulty of annotation, high-quality test suites have long been hard to obtain, while those automatically generated by LLMs tend to be superficial and lack sufficient discriminative power. As a first step toward constructing high-quality test suites, we introduce SWE-Mutation, a benchmark for evaluating LLM-generated test suites. The benchmark characterizes test suites by introducing systematically mutated solutions that attempt to ``fool'' the test suites and pass validation. We further propose an agentic, language-agnostic framework for automatically generating complex mutants. Our benchmark consists of 2,636 mutated variants derived from 800 original instances and includes a multilingual subset spanning nine programming languages. Experiments on seven LLMs reveal that even DeepSeek-V3.1 achieves only 10.20% verification and 36.15% detection rates, highlighting the inadequacy of current LLMs. Additionally, our agentic mutation strategy enhances realism, reducing average detection rates from 71.04% to 39.81% compared to conventional methods. These findings expose persistent deficiencies in the ability of current LLMs to generate reliable and discriminative test suites.

Supervised fine-tuning (SFT) on long teacher trajectories is the dominant way to instill investigation and reasoning in open software-engineering (SWE) agents. Since every retained response becomes an imitation target, the student inherits the final outcome and intermediate flaws, including ungrounded leaps and redundant loops. High-quality training data must be effective(each step is grounded and narrows the agent's epistemic gap to the correct fix) and efficient(each step is information-bearing rather than redundant or looping). Existing recipes filter or relabel teacher rollouts using only a binary terminal verifier, which does not directly target these axes and provides no supervision on instances where the teacher fails. Most real issue includes a developer-authored reference patch, $p^\star$, revealing the file paths, runtime behaviors, and coding conventions presupposed by the correct fix, yet standard pipelines discard it. We propose Patches-to-Trajectories (P2T), which uses $p^\star$ as privileged information during curation and formulates trajectory construction as bi-objective optimization over per-step effectiveness and trajectory length. A reverse phase distills $p^\star$ into a latent process graph, $G^\star$, of contextual facts and solution milestones. A forward phase curates trajectories from blinded teacher continuations by scoring per-step progress against $G^\star$ under a leakage-blocking groundedness check and retaining the shortest effective segments. Using only 1.8k curated SWE-Gym instances, P2T improves effectiveness and efficiency over outcome-filtered SFT and its tool-error-masking variant. On SWE-bench Verified, it raises Pass@1 by up to 10.8 points while reducing per-instance inference cost by ~15%, with consistent gains on SWE-bench Lite. Size-matched ablations and qualitative analysis further isolate trajectory quality from data scale.

As AI agents increasingly contribute to code development and maintenance, there is still limited empirical evidence on the quality and risk characteristics of their changes in real-world projects, particularly for refactoring-oriented contributions. It remains unclear how agent-authored refactoring edits affect maintainability, code quality, and security once merged into GitHub repositories. To address this gap, we conduct an empirical study of Python refactoring pull requests (PRs) from the AIDev dataset. We analyze agentic refactoring PRs using PyQu, an ML-based quality assessment tool for Python, to quantify changes across five quality attributes, and we complement PyQu with domain-independent static analysis (Pylint and Bandit) to measure code quality and security issues before and after each change. Our results show that, on average, agentic commits improve a quality attribute in 22.5% of the studied changes, with usability improving most frequently (36.5%). At the same time, 24.17% of modified files introduce new Pylint issues predominantly convention level violations such as long lines-while 4.7% introduce new Bandit findings. From the observed diffs, we derive a taxonomy of 24 recurring change operations and map them to the lint and security findings they most commonly affect. Despite these mixed outcomes, developer acceptance is high: 73.5% of the analyzed PRs are merged, including cases that introduce new lint or security findings, often alongside the removal of existing issues. Overall, these findings highlight both the promise and current limitations of agentic refactoring, and motivate stronger tool-in-the-loop quality and security gating for AI-driven development workflows.

Large language models show strong potential for automated code generation, but lack guarantees for correctness, quality, safety, and domain-specific constraints. For instance in robotics, where code generation is increasingly being used for planning and executing actions, awareness of the environment and physical constraints is critical. To facilitate the adaption of code-generating LLMs to diverse requirements, including domain-specific ones, we present a reinforcement learning framework that fine-tunes pre-trained LLMs using proximal policy optimization. Our customizable execution-aware reward formula captures and optimizes syntax, functional correctness, code style, security, and simulator executability. A token-level reward mapping mechanism enables effective credit assignment from execution outcomes to generated tokens. The framework is evaluated on general-purpose code generation (MBPP/MBPP+) and robotic program synthesis (RoboEval). The results show substantial improvements in functional correctness and simulator executability, including an absolute pass@1 increase of 19% on MBPP and a reduction in execution failures by 51% on RoboEval. These findings demonstrate that structured reinforcement learning can effectively align language models to correct program generation and domain-specific requirements.

Recent advances in multi-agent systems have shown great potential for solving complex tasks. However, when multiple agents edit a shared codebase concurrently, their changes can silently conflict and inconsistent views lead to integration failures. Existing multi-agent systems address this through workspace isolation (e.g., one git worktree per agent), but this defers conflict resolution to a post-hoc merge step where recovery is expensive. In this paper, we propose STORM, i.e., STate-ORiented Management for multi-agent collaboration. Specifically, STORM manages agent states by mediating their interactions with the shared workspace, ensuring that each agent operates on a consistent view of the codebase and that conflicting edits are detected and resolved at write time. We evaluate STORM on Commit0 and PaperBench across multiple LLMs. STORM outperforms the git-worktree-based multi-agent baseline by +18.7 on Commit0-Lite and +1.4 on PaperBench, while achieving comparable or better cost efficiency. Combined with single-agent runs, STORM reaches highest scores of 87.6 and 78.2 on the two benchmarks respectively, suggesting that explicit state management is a more effective foundation for multi-agent collaboration than workspace isolation. STORM can also be plugged into any multi-agent system seamlessly.

Test-time scaling has emerged as a promising approach for improving code generation by exploring large solution spaces at inference time. However, existing methods often rely on public test cases that are unavailable in practice, or require extensive LLM inference for candidate selection, leading to significant token consumption and time overhead. We present DiffCodeGen, a novel test-time scaling method for code generation based on coverage-guided differential analysis. DiffCodeGen generates diverse code candidates using various sampling and prompting strategies, then applies coverage-guided fuzzing to synthesize inputs without requiring any existing tests or large language models. By executing all candidates on these inputs, DiffCodeGen captures their dynamic behavior and clusters candidates based on behavioral similarity. DiffCodeGen selects the medoid of the largest cluster as the final output. Unlike prior test-time scaling methods that invoke additional LLM inference for candidate selection, DiffCodeGen performs selection without any extra model calls, incurring little to no additional token consumption. DiffCodeGen is fully asynchronous, naturally suited to the current trend of agentic coding, and is thus efficient and highly scalable. We evaluate DiffCodeGen across 4 large language models, demonstrating consistent improvements over baselines. Compared to state-of-the-art test-time scaling methods, DiffCodeGen achieves competitive or superior performance while using only a fraction of time and tokens. DiffCodeGen is model-agnostic and can be combined with reasoning models to further boost performance.

Agentic AI coding systems can inspect repositories, plan implementation steps, edit files, call tools, run tests, and submit pull requests. These capabilities make software and hardware development faster in some settings, but current evidence does not support the simple claim that autonomous code generation automatically improves engineering outcomes. Controlled studies report productivity gains in some enterprise tasks, slowdowns in mature open-source work, moderate but heterogeneous meta-analytic effects, and persistent failures in repository setup, dependency handling, permission gating, and hardware verification. This paper argues that the central problem is no longer prompt engineering; it is engineering process control. It synthesizes evidence from agentic software engineering, GitHub-scale adoption studies, repository-level agent configuration, productivity trials, issue-resolution benchmarks, and hardware/RTL verification research. It proposes Agentic Agile-V, a process framework that uses Agile-V as the lifecycle backbone and a task-level SCOPE-V loop - Specify, Constrain, Orchestrate, Prove, Evolve, and Verify - to convert conversational intent into structured engineering artifacts and acceptance evidence. The paper contributes: (i) a taxonomy of minimum input artifacts for agentic software, firmware, and hardware work; (ii) a conversation-to-contract gate that separates exploratory dialogue from implementation; (iii) risk-adaptive feature, bug-fix, testing, and hardware workflows; and (iv) an evidence-bundle acceptance model for agent-generated artifacts. The paper concludes that agentic AI does not eliminate engineering discipline; it increases the value of requirements, constraints, traceability, independent verification, and human approval.

Number prediction stands as a fundamental capability of large language models (LLMs) in mathematical problem-solving and code generation. The widely adopted maximum likelihood estimation (MLE) for LLM training is not tailored to number prediction. Recently, penalty-driven approaches, e.g., Number Token Loss and Discretized Distance Loss, introduce an inductive bias of numerical distance but induce over-sharpened and over-flattened digit distributions, respectively. In this paper, we make an in-depth analysis on LLM numerical learning, and show that existing numerical learning methods conceptually follow a criterion-distance formulation, where the criterion term represents optimization pattern and the distance term instills geometric prior. Consequently, we present Digit Entropy Loss (DEL) for auto-regressive numerical learning, which reformulates the conventional unsupervised entropy optimization in three key designs: leveraging digit conditional probability and binary cross-entropy to guide the entropy optimization into a supervised manner; deprecating the distance term to bypass the issue of numerical distance; and generalizing the integer-based numerical learning to floating-point number optimization, enabling more accurate number prediction. Our DEL formulation can incorporate integers, decimals, and decimal points, expanding the learning objective from a single digit to the floating-point number domain. Experiments conducted on seven mathematical reasoning benchmarks with four representative LLMs, including CodeLlama, Mistral, DeepSeek, and Qwen-2.5, demonstrate that DEL consistently outperforms its counterparts in both overall prediction accuracy and numerical distance. Source codes are at https://github.com/PolyU-VCLab/DEL

Recent work pairs LLMs with evolutionary search to iteratively generate, modify, and select code using task-specific feedback. These systems have produced strong results in mathematical discovery and algorithm design, yet a fundamental question remains: what do they actually evolve? Progress is typically summarized by the best score a run reaches under a task-specific evaluator, but that score can reflect several different mechanisms: new algorithmic structure, re-tuning an existing strategy, recombining ideas already in the model's internal knowledge, or overfitting to the evaluator. Distinguishing these mechanisms requires inspecting the search process itself, not only its final outcome. We introduce EvoTrace, a dataset of evolutionary coding traces spanning four evolutionary frameworks, reasoning and non-reasoning models, and 16 tasks across mathematics and algorithm design. To analyze these traces, we develop EvoReplay, a replay-based methodology that reconstructs the local search states behind high-scoring solutions and tests controlled interventions, including adjusting constants, removing program components and substituting models or prompting contexts. We annotate every code edit in EvoTrace with one of nine recurring edit types using an LLM-as-judge pipeline validated against blind human re-annotation. Across EvoTrace, most score gains come from a small subset of these edit types. We further find a deterministic cycling pattern: about 30% of code lines added during search are byte-identical re-introductions of previously-deleted lines, present throughout nearly every run. These results show that benchmark gains in evolutionary coding agents can arise from qualitatively different mechanisms, only some of which correspond to new algorithmic structure. EvoTrace enables more diagnostic evaluation of evolutionary coding agents beyond final benchmark scores.

Explicit software architecture models are essential artifacts for communicating, analyzing, and evolving complex software-intensive systems. In ROS2-based robotic systems, however, structural (de-)composition and integration semantics are often only implicitly encoded across distributed artifacts such as source code and launch files, making recovery of hierarchical architecture particularly difficult. Existing approaches mainly focus on node-level entities and communication wiring, while providing limited support for recovering hierarchical structural (de-)composition across multiple abstraction levels. In this paper, we extend our previously proposed blueprint-guided LLM-assisted architecture recovery pipeline for ROS2 systems through two major enhancements: (1) refined prompting to improve the consistency and controllability of architecture synthesis, and (2) a staged recovery strategy based on multi-level intermediate architectural representations that incorporate the atomic ROS node list and launch file dependencies, thereby enabling structurally constrained reconstruction across multiple abstraction levels. The approach is evaluated on a real-world automated product disassembly system based on cooperative robotic arms and heterogeneous ROS2 artifacts. Compared to our previous work, the considered case study exhibits substantially higher integration complexity and richer functionality. The results demonstrate improved structural consistency, scalability, and robustness of architecture recovery, while also revealing remaining challenges related to dynamic integration semantics in large-scale ROS2 systems.

As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question unanswered: does the structural and stylistic quality, or ``cleanliness'' of the underlying code affect an agent's ability to navigate and modify it? To isolate the effect of code cleanliness from agent capability, we introduce an evaluation protocol built around minimal pairs: repositories that match on architecture, dependencies, and external behaviour, but differ on static-analysis rule violations and cognitive complexity. The pairs are constructed in both directions, by agent pipelines that either degrade a clean repository or clean a messy one. We author 33 tasks across six such pairs, evaluated through hidden tests at the application's public surface. Across 660 trials with Claude Code, code cleanliness does not change the agent's pass rate. However, it substantially alters the agent's operational footprint: agents working on cleaner code use 7 to 8% fewer tokens and reduce file revisitations by 34%. Our findings suggest that traditional maintainability principles remain highly relevant in the era of AI-driven development, shaping the computational cost and navigational efficiency of coding agents. Code cleanliness joins model choice, harness, and prompting as a factor that materially affects agent behaviours.

Offline reinforcement learning (RL) offers a promising route for developing plasma controllers from historical tokamak data, since online trial-and-error on real devices is costly and risky. However, progress in this direction remains difficult to measure due to the lack of a standardized offline RL benchmark for realistic multi-actuator, long-horizon plasma control problems in nuclear fusion. We introduce RL4F, an Offline Reinforcement Learning Benchmark for Plasma Control in Nuclear Fusion, providing closed-loop evaluation environments and baseline comparisons across four full-profile tracking tasks: rotation, density, temperature, and pressure. The dynamics function underlying the evaluation environment is built from historical discharge data from DIII-D, a real-world Tokamak. We evaluate a broad set of imitation learning and offline RL baselines under a unified protocol. We find that offline model-based RL methods obtain the best average performance on most objectives, although no single method dominates all tasks, highlighting the importance of dynamics modeling in complex, long-horizon plasma control tasks. To foster further research, we open-source the codebase, datasets, and evaluation framework, providing a benchmark not only for the fusion community but also for algorithm development in offline RL.

We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1) app-specific state verifiers that expose structured inspection endpoints over real applications, (2) a self-evolving verification layer that improves verifier reliability using execution-grounded feedback, (3) a task-generation pipeline that synthesizes realistic and machine-checkable desktop tasks, and (4) an evaluation harness that records full trajectories and computes auditable partial-credit rewards. In its current form, OpenComputer covers 33 desktop applications and 1,000 finalized tasks spanning browsers, office tools, creative software, development environments, file managers, and communication applications. Experiments show that OpenComputer's hard-coded verifiers align more closely with human adjudication than LLM-as-judge evaluation, especially when success depends on fine-grained application state. Frontier agents struggle with end-to-end completion despite partial progress, and open-source models exhibit sharp drops from their OSWorld-Verified scores, exposing a persistent gap in robust computer automation.

Pairwise human preference prediction is central to evaluating code-generation systems, where quality often depends on task-specific trade-offs beyond functional correctness. While rubric-based LLM judges improve interpretability by decomposing evaluation into explicit criteria, most existing pipelines remain pointwise: they score each response independently and derive preferences by comparing aggregated scores. We show that this design is poorly matched to pairwise code preference prediction and can underperform a strong monolithic judge. We propose CriterAlign, a criterion-centric framework that adapts rubric-based judging to pairwise preference evaluation through direct criterion-level pairwise judgments, tie-driven criterion refinement, swap-consistency filtering, and final pairwise synthesis. We further introduce Human-Preference-Aligned Guidance (HPAG), synthesized offline from training examples by extracting recurring rationale gaps between human preferences and monolithic judge predictions, and injected into the criterion generator, criterion judge, and final judge. On BigCodeReward, CriterAlign improves a Qwen2.5-VL-32B monolithic judge from 60.4% to 66.3% accuracy, with ablations confirming the contributions of pairwise criterion design and HPAG.

AI-based code assistants are transforming software development, yet we lack empirical evidence on how they affect developers' cognitive processes. We present a multisite study investigating the neurophysiological correlates of AI-assisted programming through a within-subjects crossover design. We recruited participants at two universities (Bari, Italy, and Copenhagen, Denmark) and collected electroencephalography, eye-tracking, electrodermal activity, and heart rate variability data alongside a rubric-based performance score and self-reported workload across six dimensions using the NASA Task Load Index (NASA-TLX). We tested four hypotheses addressing physiological differences between AI-assisted and non-assisted conditions, the moderating role of developer experience, the association between physiology and performance, and the alignment between subjective perceptions and objective measures. Under AI assistance, the EEG $θ/α$ ratio was lower during the first task and the gaze blink rate was higher during the second, both consistent with reduced cognitive engagement when developers offload generative effort to the model. This pattern did not differ between undergraduate and graduate students. Electrodermal activity correlated with performance under the non-AI condition but not under AI. Among the six NASA-TLX dimensions of self-reported workload, only Physical demand was associated with performance under the non-AI condition but not under AI. These findings suggest that AI-assisted programming is not a faster version of solo coding but a cognitively distinct activity, with implications for the design of AI assistants and for biometric monitoring in AI-augmented development.

Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification. We frame this shift through the lens of agent harnesses and introduce code as agent harness: a unified view that centers code as the basis for agent infrastructure. To systematically study this perspective, we organize the survey around three connected layers. First, we study the harness interface, where code connects agents to reasoning, action, and environment modeling. Second, we examine harness mechanisms: planning, memory, and tool use for long-horizon execution, together with feedback-driven control and optimization that make harness reliable and adaptive. Third, we discuss scaling the harness from single-agent systems to multi-agent settings, where shared code artifacts support multi-agent coordination, review, and verification. Across these layers, we summarize representative methods and practical applications of code as agent harness, spanning coding assistants, GUI/OS automation, embodied agents, scientific discovery, personalization and recommendation, DevOps, and enterprise workflows. We further outline open challenges for harness engineering, including evaluation beyond final task success, verification under incomplete feedback, regression-free harness improvement, consistent shared state across multiple agents, human oversight for safety-critical actions, and extensions to multimodal environments. By centering code as the harness of agentic AI, this survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.

AI-assisted research is crossing a threshold: fully automated systems can now generate research papers for as little as $15, while long-horizon agents can execute experiments, draft manuscripts, and simulate critique with minimal human input. Yet this productivity frontier exposes a deeper integrity problem: under scientific pressure, even frontier LLMs still fabricate results, miss hidden errors, and fail to judge novelty reliably. Studying developments through April 2026, we present an end-to-end analysis of AI across the complete research lifecycle, organized into four epistemological phases: Creation (idea generation, literature review, coding & experiments, tables & figures), Writing (paper writing), Validation (peer review, rebuttal & revision), and Dissemination (posters, slides, videos, social media, project pages, and interactive agents). We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy: AI excels at structured, retrieval-grounded, and tool-mediated tasks, but remains fragile for genuinely novel ideas, research-level experiments, and scientific judgment. Generated ideas often degrade after implementation, research code lags far behind pattern-matching benchmarks, and end-to-end autonomous systems have not yet consistently reached major-venue acceptance standards. We further show that greater automation can obscure rather than eliminate failure modes, making human-governed collaboration the most credible deployment paradigm. Finally, we provide a structured taxonomy, benchmark suite, and tool inventory, cross-stage design principles, and a practitioner-oriented playbook, with resources maintained at our project page.

Machine learning-based malware detectors are widely deployed in antivirus and endpoint detection systems, yet their reliance on static features makes them vulnerable to adversarial manipulation. This paper investigates whether a malware sample can be intentionally misclassified as a specific benign software category, not merely as "not malware", by adding a small number of Win32 API imports characteristic of that selected category, without removing any existing imports or retraining the detector. We propose a framework centered on a Conditional Variational Autoencoder (CVAE) whose decoder is strictly additive. It can introduce new API calls but never remove existing ones, preserving malware functionality by design. For each malware sample, the framework automatically identifies which benign category it most closely resembles and uses that as the evasion target. A knowledge-distilled differentiable proxy enables gradient-based training against the non-differentiable ensemble detector. Experiments on a six-class dataset of binary Win32 API import vectors extracted from 3,799 Windows executables (five benign categories, one malware class) show that, against a detector achieving 87.5% malware recall, adding just 20 API imports reduces recall to 30%. At k=20, among samples that evaded detection, 99% are classified as the intended target category. The CVAE outperforms both a frequency-based baseline and random selection at every tested injection size (k = 5 to 50). Validation on real PE files submitted to VirusTotal confirms that the attack transfers to commercial static detection engines, with an average 54.5% reduction in flagging engines. These findings expose a concrete vulnerability in API-based malware classifiers and demonstrate that targeted evasion into a chosen benign category is achievable with minimal, functionality-preserving modifications.

Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites configuration the user never mentioned. We call these scope expansions overeager actions, an authorization problem distinct from capability failures, prompt injection, or sandbox escapes. We present OverEager-Gen, a benchmark dedicated to overeager behavior on benign tasks. Building it surfaces a measurement-validity issue: if a benchmark spells out the authorized scope inside the prompt, the agent stops inferring boundaries and starts pattern-matching declaration text. On Claude Code, stripping the consent declaration alone raises the overeager rate from 0.0% to 17.1% on paired scenarios (McNemar exact p = 2.4 x 10^-4). OverEager-Gen therefore certifies each scenario's discriminative power before admission via a behavioral-gradient validator, audits internal tool calls through a dual-channel stack (PATH-injected shim plus per-agent event streams), and ships byte-identical consent_kept and consent_stripped variants. OverEager-Bench contains 500 validated scenarios and ~7,500 runs across four agent products (Claude Code, OpenHands, Codex CLI, Gemini CLI) and six base models; a 50-sample re-annotation gives Cohen's kappa = 0.73 and rule-judge recall = 1.00. Stripping consent multiplies the overeager rate on every shared base model (Delta in [11.9, 17.2] pp). The framework axis dominates effect size: a permissive cluster (Claude Code, Codex CLI, Gemini CLI) runs at 5.4-27.7% while the ask-to-continue framework (OpenHands) sits at 0.2-4.5% (Fisher p <= 10^-5). Within-framework base-model variance reaches 15.9 pp, indicating that model-layer alignment does not fully propagate through permissive permission gating.

In retrieval-augmented coding, failures often begin when the relevant file is absent from the retrieved context. Under frozen generic tokenization, where a BM25 index has been built by a search system whose analyzer the practitioner does not control, this failure is routine: BM25's logarithmic RSJ-odds IDF under-separates the identifier tail that distinguishes one function from another. We replace the outer logarithm of the Robertson-Spärck-Jones odds with a q-logarithm. At q=1 the transform recovers BM25 exactly by L'Hôpital's rule, and for q<1 it is a Box-Cox transform of the RSJ odds with lambda = 1-q. On CoIR CodeSearchNet Go (182K documents), oracle-tuned NDCG@10 rises from 0.2575 to 0.4874 (absolute +0.2299; +89.3% relative; zero sign reversals in 10,000 paired-bootstrap resamples, reported as p <= 10^-4). The effect is graded across code languages and is near-zero on BEIR text. A one-parameter closed form estimates a corpus-level q from hapax density and stays near q=1 on corpora where BM25 is already optimal. The index-time cost is a single pass over the sparse score matrix and query latency is unchanged. A tokenizer ablation shows that identifier-aware tokenization largely removes the incremental gain from q-IDF.

Software repositories accumulate large amounts of unstructured knowledge in commit messages, pull-request discussions, and issue threads, but developers and AI coding assistants rarely reuse this history effectively. Recent work on typed-memory architectures for LLM agents (MemGPT, generative agents, and the PlugMem module of Yang et al.) argues that agent memory should be distilled, typed knowledge rather than raw interaction text. We adapt that stance to a software repository's own git history under a constrained regime: deterministic, dependency-free, local-only, no embeddings. We present CommitDistill, an open-source Python prototype that mines a local git history into typed knowledge units (Facts, Skills, Patterns) using deterministic regex and surfaces them through a TF-IDF retriever with a calibrated silence threshold (theta = 2.5) that abstains on out-of-distribution queries. The artefact is a trust-instrumented memory substrate: deterministic, no external service, inspectable plain-JSON store, tunable abstention. A case study on five public repositories spanning Python, JavaScript, C, and Java (25,000 commits, 1,167 extracted units) reports useful-precision 0.525 at Cohen's kappa = 0.633 on 40 dual-annotated Python units. The decisive finding is budget-constrained retrieval: at a 256-character per-query budget, CommitDistill reaches 0.750 hit-rate on a 12-query benchmark against BM25's 0.333 and git log --grep's 0.083. On a four-arm paired LLM-as-judge evaluation (n=200 time-travel bug-fixes, two judges) covering control, CommitDistill, a body-budget-matched CD-Hybrid, and BM25, no condition produces a statistically detectable lift over control on the headline mean and CD-Hybrid is indistinguishable from BM25 head-to-head. Extraction over 10,000 commits completes in under 4 seconds on a laptop. Source, annotations, baselines, and a reproducibility script accompany this paper.

Large Language Models (LLMs) demonstrate strong potential for automated code generation, yet their ability to iteratively refine solutions using execution feedback remains underexplored. Competitive programming offers an ideal testbed for this investigation, as it demands end-to-end algorithmic reasoning, precise implementation under strict computational constraints, and complete functional correctness with rigorous evaluation. In this paper, we present A-ProS, an autonomous AI agent that solves competitive programming problems through a hybrid multi-model feedback framework separating solution generation from specialized debugging. A-ProS combines ChatGPT-based generators (GPT-4 and GPT-5) with three debugging critics: Codestral-2508, Llama-3.3-70B, and DeepSeek-R1, under a 2 x 3 factorial design. We evaluate six workflows on 367 problems from ICPC World Finals (2011-2024) and Codeforces (rated 1200-1800). The results show that GPT-5 workflows improve from 39 initial accepted solutions to 85-90 after three refinement rounds, while GPT-4 improves from 15 to 31-38. A controlled ablation on 47 problems shows that stateful refinement outperforms stateless approaches by 8.5-10.6 percentage points and reduces repeated failures by up to 3.5x. Compared to baseline agent loops, A-ProS achieves over 2x greater gains, highlighting the importance of persistent context and multi-model feedback for reliable autonomous program synthesis.

Existing benchmarks for LLM coding agents primarily evaluate final outcomes. While useful for measuring overall capability, these metrics provide limited visibility and often miss defects that arise during execution. We present ProcCtrlBench, a benchmark for execution-process evaluation in LLM coding agents. ProcCtrlBench organizes recurrent execution defects into a reusable ontology covering 11 defect types in 4 categories, and evaluates agent trajectories through standardized process evidence rather than final outcomes alone. To support comparison across heterogeneous agents, ProcCtrlBench standardizes raw logs into a unified trajectory representation and reports calibrated scorecards over process-level findings. In addition, ProcCtrlBench uses control preservation as a way to quantify execution-process quality, capturing whether execution remains interpretable, interruptible, correctable, reversible, and able to hand back authority when needed. We evaluate ProcCtrlBench on 200 cases sampled from three benchmarks: AndroidBench, TerminalBench, and SWE-bench-Verified. Results show that ProcCtrlBench can be instantiated with useful reliability, provides more stable semantics than direct thresholding, and reveals meaningful differences in execution quality that are often overlooked by conventional outcome-based evaluation.

Vectorization via Single Instruction, Multiple Data (SIMD) architectures is a cornerstone of high-performance computing. To fully exploit hardware potential, developers often resort to explicit vectorization using intrinsics, as compiler-based auto-vectorization frequently yields suboptimal results due to conservative static analysis. While Large Language Models (LLMs) have demonstrated remarkable proficiency in general code generation, they struggle with explicit vectorization due to the scarcity of high-quality corpora and the strict semantic constraints of low-level hardware instructions. In this paper, we propose AutoVecCoder, a novel framework designed to empower LLMs with the capability of automated explicit vectorization. AutoVecCoder integrates two core components: VecPrompt, an automated data synthesis pipeline to inject domain-specific intrinsic knowledge; and VecRL, a reinforcement learning framework that aligns code generation with execution efficiency. AutoVecCoder-8B trained by this framework achieves state-of-the-art performance on the SSE and AVX subsets of SimdBench and, in some cases, generates implementations surpassing standard -O3 optimizations, effectively overcoming the inherent bottlenecks of traditional automated vectorization.

Code reasoning refers to the task of predicting the output of a program given its source code and specific inputs. It can measure the reasoning capability of large language models (LLMs) and also benefit downstream tasks such as code generation and mathematical reasoning. Existing work has verified the effectiveness of reinforcement learning on the task. However, these methods design rewards solely based on final outputs or coarse-grained signals, and neglect the inherent consistency of the stepwise reasoning process in the task. Therefore, these methods often result in sparse reward or reward hacking, which limits the full play of enhanced learning capabilities. To alleviate these issues, we propose CodeThinker, a consistency-driven reinforcement learning framework for code reasoning. Specifically, CodeThinker has three key components: (1) a stepwise reasoning-aware model training module, which utilizes a consistency tracing paradigm as a template to synthesize training data that captures the stepwise reasoning process; (2) a dynamic beam sampling strategy, which aims to improve the quality of sampled outputs under a fixed sampling budget; and (3) a consistency reward mechanism that can effectively alleviate reward hacking. Experiments on three popular benchmarks show that CodeThinker achieves state-of-the-art performance across multiple LLMs. For instance, it outperforms the strongest baseline by 4.3% in accuracy when deployed on Qwen2.5-Coder-7B-Instruct. We also validate the effectiveness of CodeThinker on downstream tasks. Results show that, without additional training, CodeThinker obtains average accuracy gains of 5.33 and 3.11 percentage points on mathematical reasoning and code reasoning tasks covering 17 programming languages, respectively.

Coding agents are increasingly used as application builders, yet many evaluations still focus on source code, repository-level tests, or intermediate traces rather than the delivered application. We introduce WebGameBench, a requirement-to-application benchmark that evaluates whether coding agents can turn a frozen Structured WebGame Specification into a browser-accessible game. Browser-native games provide a compact but behavior-dense testbed: even simple games require coordinated input handling, spatial mapping, rule execution, state transitions, terminal conditions, restart behavior, and visible feedback. In WebGameBench, each generated artifact is built, served, and exposed as a browser-accessible application under a unified deployment protocol. A runtime evaluator then interacts with the delivered game in a real browser and assigns a three-way label: EXCELLENT, USABLE, or UNUSABLE. On a human-reviewed subset, the runtime label is broadly aligned with human gameplay review under the Usable-rate criterion. Across 111 tasks, 12 coding agents, and 14 evaluation configurations, WebGameBench separates current systems: the best configuration reaches a 76.9% usable rate but only a 20.2% excellent rate. This gap shows that crossing the minimum playable-delivery threshold is still far from complete requirement satisfaction. To our knowledge, WebGameBench is the first requirement-to-application benchmark for browser-native game delivery that validates delivered-application runtime labels against independent human gameplay review under the Usable-rate criterion.

Test-time scaling is an important mechanism for improving large language models, especially on tasks with deterministic verifiers. Code translation is a canonical example: the source program constrains valid outputs, while compilers, type check- ers, and behavioral checks provide exact pass/fail feedback. Existing approaches typically apply these verifiers only after generation, which is inefficient because early errors corrupt the autoregressive context and are rarely corrected later. We introduce Decoding Time Verification (DTV), a framework that treats structural boundaries as meta steps for verifier-guided decoding. DTV interleaves generation with verifier calls under a state-machine controller that enforces valid prefixes, using structural-boundary checks and structure-aware rollback to prevent error propagation while reducing wasted tokens. We evaluate DTV on C-to-Rust and JavaScript-to-TypeScript translation. Using Qwen3-4B as the primary generator under matched token budgets, DTV improves pass rates from 72.3% to 82.0% on C-to-Rust and from 33.3% to 46.0% on JavaScript-to-TypeScript relative to matched self-refinement baselines, while using fewer tokens per case; the same trend largely transfers to Gemma-4-E4B. In the evaluated cost-matched grid, DTV achieves a more favorable pass-rate-cost tradeoff than post-hoc verification or sampling-based scaling. These results show that verifier-guided decoding is an effective use of inference-time compute for code translation.

Software fault prediction (SFP) is a critical task in software engineering, enabling early identification of faults in modules to improve software quality and reduce maintenance costs. This research investigates the combined effects of feature selection and parameter tuning on the performance of machine learning (ML) models for SFP. This study evaluates the interaction between feature selection methods, including correlation-based feature selection (CFS), recursive feature elimination (RFE), mutual information (MI), and L1 regularization, where hyperparameter tuning techniques such as grid search, randomized search, and genetic algorithm (GA) are used for optimization of ML algorithms, including random forest (RF), logistic regression (LR), and support vector machines (SVM) for optimized fault prediction performance. The combined application of CFS and GA yielded the highest accuracy, achieving 88.40% with RF, representing an improvement of 18% over baseline models without feature selection or tuning. Feature selection reduced dimensionality and identified critical attributes such as weighted methods per Class (WMC) and coupling between objects (CBO), while iterative parameter tuning optimized model alignment to these feature sets. Notably, the proposed methods demonstrated robustness, with minimal cross-validation variability (+-1.0%), and efficiency, reducing training times in univariate methods such as L1 regularization.