Repository-level repair benchmarks still center on a few mainstream languages, leaving systems languages such as Odin largely untested. We present OdinEval, a reproducible benchmark built from documented defects in public Odin repositories. Each instance binds an issue to base and fix commits, a gold patch, an issue-specific regression test, a historical toolchain, and execution records. Admission requires the test to fail on the base revision and pass after the gold fix. When no usable developer test exists, a black-box test is reviewed independently by three instances of the same model, executed in both historical states, and revised from recorded feedback under a versioned Test Writing Skill. We evaluate six language models on 168 filtered instances under one shared protocol. Kimi-K3 records the highest Resolved score at 66.7%, while Qwen3.8-Max has the highest Repro score at 96.4%. The release includes frozen data, source archives, containers, validators, model patches, and audit manifests.
软件工程与仓库智能 7/30
ORCA: Observability-Grounded Program Repair for Microservice Incidents
作者：Yuanchen Gao、Yifang Tian、Yiran Li、Charles Zhang、Hans-Arno Jacobsen 机构：香港科技大学（Hong Kong University of Science and Technology）；多伦多大学（University of Toronto）。
Microservice failures are often diagnosed from operational telemetry. However, automated program repair systems usually start from issue reports, localized code context, or failing tests. This mismatch leaves a gap between telemetry-based diagnosis and patch generation. We present ORCA, an observability-grounded APR pipeline for microservice incidents. ORCA first distills the differences in paired failure and reference telemetry into a fault signature, then uses the signature to identify candidate code and deployment-configuration locations. Repair graph agents and an Exploration agent generate unified-diff patch candidates from these locations. ORCA evaluates generated patches with a Telemetry-Grounded Patch Verifier that separates patch validity, syntactic and semantic correctness, test-oracle integrity, and telemetry replay. On a 575-case benchmark, ORCA outperforms all evaluated baselines in terms of cost-effectiveness. Results show that operational telemetry can be transformed from diagnostic evidence into actionable repair context: paired telemetry supports repair-oriented localization, while repair graph agents convert localized code and configuration evidence into constrained patch-generation context for the LLM. Telemetry-grounded verification then exposes repair outcomes that issue- or test-only evaluation would miss.
软件工程与仓库智能 7/30
TDD-Agent: Test-Driven Reasoning for Code Generation
Large Language Models (LLMs) have achieved remarkable progress in code generation, yet ensuring correctness in complex, repository-level tasks remains challenging. Existing approaches often use generated tests as static post-hoc validators, which limits their ability to guide implementation and may introduce misleading feedback when the tests themselves are incomplete or incorrect. In this paper, we introduce TDD-Agent, which operationalizes the test-driven development paradigm for code generation. TDD-Agent first prompts the model to generate executable tests, encouraging it to clarify expected behaviors before implementation, and then performs iterative dual-track refinement over both the generated code and tests using execution feedback. We first isolate the effect of test-first reasoning through a prompt variant TDD-prompt on LiveCodeBench, where it consistently improves upon reasoning-based prompting baselines. Building on this finding, we evaluate the full TDD-Agent framework on RepoEval, a repository-level benchmark, and show that it consistently outperforms retrieval-based and agent-based baselines. Additional analyses show that iterative refinement improves not only code correctness but also the effectiveness of the generated tests, yielding higher pass rates, coverage, and mutation scores, suggesting that tests can serve as evolving reasoning artifacts rather than fixed validators. Our source code is available at https://anonymous.4open.science/r/TDD-Agent-Framework-6370/.
软件工程与仓库智能 7/30
The Specification Paradox: Rethinking Requirements Engineering in the Age of AI
作者：Tassio Sirqueira、Jessica Faciroli 机构：Tassio Sirqueira, Dept. Computer Science, Inst. Mathematics & Statistics, Rio de Janeiro State Univ. Jessica Faciroli, Faculty of Economics, Rio de Janeiro State Univ.
The growing adoption of Large Language Models (LLMs) in Software Engineering has reinforced the expectation that coding activities can be largely automated. However, this perception may represent yet another historical search for a solution capable of eliminating the inherent challenges of software development. This article discusses the transition from a code-centered paradigm to Specification-Driven Development. We argue that artificial intelligence reduces some of the effort associated with writing source code, but it does not eliminate the complexity of developing professional software systems. Instead, it shifts this complexity toward domain understanding, requirements elicitation, specification development, validation, maintenance, and software evolution. Building on this perspective, we discuss the renewed centrality of Requirements Engineering, considering its implications for productivity and software quality, as well as risks associated with automation bias, ambiguity propagation, Specification Overfitting, and the accumulation of Specification Debt. Finally, we propose the Specification Paradox: the more capable artificial intelligence systems become at automatically generating software, the greater the dependence on correct, complete, verifiable, and explainable human-produced specifications. We conclude that the future of Software Engineering will depend not only on machines' ability to generate code, but also on humans' ability to correctly specify, evaluate, and evolve what is intended to be built.
形式化与程序验证 · 3/30 · 2026-08-19从盲区自我演化的评估指标借鉴程序验证的反例引导抽象精化，从评估器盲区碰撞中自动演化缺陷标记算子Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots
Agents improve quickly against a reliable automatic metric and stall without one, and the applications that need them most, report generation among them, are the ones nobody knows how to score. Can the metric write itself? Saying what makes an answer good is hard; pointing at something wrong with one is easier, so the metric we evolve is a pool of small Python operators that each flag a candidate for one named defect, or abstain, and vote. Asking a model for operators directly does not work: 183 candidates realise only 96 distinct behaviours, from one narrow region of an enormous space. EvalCEGAR instead borrows counterexample-guided abstraction refinement from program verification. It reads the pool as an abstraction and searches for a collision, two answers the operators score identically, one correct and one not. That pair, not a prompt, is the authoring request, and when a collision defeats every attempt the loop widens what an operator may read rather than resampling. On MBPP+ and HumanEval+, a sandbox whose hidden unit tests give exact ground truth, the loop writes a 55-line operator that closes 15.4% of the gap between flagging nothing and a perfect filter on 428 unseen tasks (+0.0065, p=0.0010) at a quarter of our best hand-written operator's flags. On the benchmark it never saw it matches that operator's effect exactly on a third of the flags. Six of eight runs admit such an operator and all six help out of sample; our 15 hand-written operators applied together as one filter lose accuracy. An LLM judge on the same information ties that delta on a nearly disjoint set of candidates, and charges a model call per candidate forever where the operator charges none.
阅读 arXiv 原文形式化与程序验证 · 3/30 · 2026-08-19覆盖驱动的RTL断言生成框架结合形式化迹生成、语法引导合成与神经符号精化，提升硬件断言覆盖完备性Coverage-Driven RTL Assertion Generation with Formal Exploration and Neuro-Symbolic Refinement
Hardware functional verification relies on high-quality assertions to expose design bugs and establish confidence in Register Transfer Level (RTL) designs. Yet existing assertion mining methods still struggle to produce complete and reliable assertion sets: random or limited traces fail to cover hard-to-reach behaviors, and one-shot generation provides little feedback about what remains unverified or how the assertion set should be improved. As a result, critical design behaviors can remain uncovered even when many assertions are generated. We present NeuroAssertion, a coverage-driven assertion generation framework that combines formal trace generation, syntax-guided synthesis (SyGuS), and an agent-inspired refinement process within a unified framework. Our framework first converts hard-to-reach control-flow conditions into formal reachability objectives, uses model checking to generate behaviorally diverse traces, and mines initial assertions from these traces with SyGuS. It then performs targeted agent-inspired refinement under verification feedback: one LLM first proposes candidate assertions for uncovered regions, and if a candidate fails formal checking, a second LLM generates a repair grammar that guides constrained symbolic synthesis in a neuro-symbolic repair procedure. Experimental results show that this framework delivers around 2X more assertions and about 2X higher mutation coverage than traditional assertion mining methods.
软件工程与仓库智能 · 9/30 · 2026-08-19Odin语言程序修复基准OdinEval基于公开仓库缺陷构建的可复现基准含168实例，评估六个语言模型的修复与复现表现OdinEval: A Reproducible Benchmark for LLM-Based Program Repair in the Odin Programming Language
Repository-level repair benchmarks still center on a few mainstream languages, leaving systems languages such as Odin largely untested. We present OdinEval, a reproducible benchmark built from documented defects in public Odin repositories. Each instance binds an issue to base and fix commits, a gold patch, an issue-specific regression test, a historical toolchain, and execution records. Admission requires the test to fail on the base revision and pass after the gold fix. When no usable developer test exists, a black-box test is reviewed independently by three instances of the same model, executed in both historical states, and revised from recorded feedback under a versioned Test Writing Skill. We evaluate six language models on 168 filtered instances under one shared protocol. Kimi-K3 records the highest Resolved score at 66.7%, while Qwen3.8-Max has the highest Repro score at 96.4%. The release includes frozen data, source archives, containers, validators, model patches, and audit manifests.
代码质量与优化 · 3/30 · 2026-08-19攻破视觉语言模型的薄弱环节研究视觉语言模型在视觉输入对抗扰动下的逃逸攻击，提出基于梯度的攻击方法，覆盖目标与非目标场景Breaking the weakest link to evade vision language models
Vision Language Models (VLMs) have recently emerged as a critical component of multimodal AI systems, enabling joint reasoning over visual and textual inputs in real-world and safety-critical applications. Despite their growing deployment, the robustness of VLMs against adversarial threats remains insufficiently explored, particularly in the context of evasion attacks targeting multimodal alignment. In this work, we investigate the vulnerability of VLMs to adversarial perturbations applied to visual inputs and study two attack settings: untargeted attacks, where the goal is to disrupt the model's interpretation of the original image, and targeted attacks, where the adversary aims to force the model to generate a specific semantic description unrelated to the original image. To efficiently generate adversarial examples, we propose a gradient-based attack method that performs optimization exclusively on the vision encoder of the VLM rather than on the entire multimodal architecture. This design significantly reduces the computational cost and resource requirements of the attack while maintaining strong effectiveness. We evaluate our approach on several open-source VLMs, including Qwen2.5-VL, Granite-Vision, FastVLM, and Phi-3.5-Vision, and show that small, human-imperceptible perturbations can substantially alter the textual interpretation produced by the models. Our findings highlight the vulnerability of modern VLMs to adversarial manipulation and emphasize the need for improved robustness and security mechanisms in multimodal AI systems.