代码大模型 / AI 编程

Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair

Yuxiang Wei, Chunqiu Steven Xia, Lingming Zhang

专题命中 程序修复 ：program repair(title,abstract)；code generation(abstract)；分类 cs.SE、cs.LG、cs.PL

Comments Paper accepted at ESEC/FSE 2023

Project Prometheus: Bridging the Intent Gap in Agentic Program Repair via Reverse-Engineered Executable Specifications

普罗米修斯计划：通过反向工程可执行规范弥合代理程序修复中的意图差距

Yongchao Wang, Zhiqiu Huang

机构 * Nanjing University of Aeronautics and Astronautics（南京航空航天大学） 纠错

专题命中 程序修复 ：program repair(title,abstract)；code generation(abstract)；分类 cs.SE、cs.AI

AI总结 本文提出普罗米修斯框架，通过规范推断而非代码生成解决代理程序修复中的意图差距问题，实现了93.97%的正确补丁率和74.4%的救援率。

HAFixAgent: History-Aware Program Repair Agent

HAFixAgent：基于历史的程序修复代理

Yu Shi, Hao Li, Bram Adams, Ahmed E. Hassan

机构 * Queen's University（女王大学） 纠错

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE、cs.AI

AI总结 本文提出HAFixAgent，通过注入历史衍生的仓库启发式方法，提升大规模多补丁bug修复的效率与鲁棒性，实验证明其在Defects4J和BugsInPy上均优于现有方法。

Comments support both Defects4J and BugsInPy; use the same LLM for all baseline comparisons; add sensitivity analysis for imperfect fault localization

A Study on the Impact of Fault localization Granularity for Repository-Scale Code Repair Tasks

对仓库级代码修复任务中故障定位粒度影响的研究

Joseph Townsend, Chandresh Pravin, Kwun Ho Ngan, Matthieu Parizy

机构 * Fujitsu Research of Europe（富士通欧洲研究院） 纠错

专题命中 程序修复 ：repository(title,abstract)；program repair(abstract)；分类 cs.SE、cs.AI

AI总结 研究探讨了仓库级代码修复中故障定位粒度对修复效果的影响，提出框架验证不同粒度下的修复率，并指出任务依赖性可能影响最佳粒度。

Monte Carlo Tree Search for Execution-Guided Program Repair with Large Language Models

基于大语言模型的执行引导程序修复的蒙特卡罗树搜索

Yixuan Liang

机构 * Illinois Institute of Technology Chicago, USA（伊利诺伊理工学院芝加哥分校） 纠错

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE、cs.LG

AI总结 CodePilot结合MCTS和大语言模型，通过执行反馈引导程序修复，实现高效的问题解决。

Comments 10 pages, 5 figures. Submitted to a conference workshop

Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair

回避与验证：一种双LLM策略用于减少代理程序修复中的噪声

José Cambronero, Michele Tufano, Sherry Shi, Renyao Wei, Grant Uy, Runxiang Cheng, Chin-Jung Liu, Shiying Pan, Satish Chandra, Pat Rondon

机构 * Google, USA（谷歌公司） ； Meta, USA（Meta公司） 纠错

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE、cs.AI

AI总结 本文提出双LLM策略，通过bug回避和补丁验证减少代理程序修复中的噪声，提升修复成功率和可靠性。

Comments Accepted to the 2026 IEEE/ACM 48th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP '26)

Journal ref 2026 IEEE/ACM 48th International Conference on Software Engineering (ICSE-SEIP '26)

RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models

Jingjing Liu, Zeming Liu, Zihao Cheng, Mengliang He, Xiaoming Shi, Yuhang Guo, Xiangrong Zhu, Yuanfang Guo, Yunhong Wang, Haifeng Wang

机构 * School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院） ； East China Normal University（华东师范大学） ； School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院） ； Baidu Inc.（百度公司） 纠错

专题命中 程序修复 ：repository(title,abstract)；program repair(abstract)；分类 cs.SE、cs.AI

Comments 30 pages, 12 figures, EMNLP 2025 Findings

SemAgent: A Semantics Aware Program Repair Agent

Anvith Pabba, Alex Mathai, Anindya Chakraborty, Baishakhi Ray

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE、cs.AI

Evaluating Agent-based Program Repair at Google

Pat Rondon, Renyao Wei, José Cambronero, Jürgen Cito, Aaron Sun, Siddhant Sanyam, Michele Tufano, Satish Chandra

专题命中 程序修复 ：program repair(title,abstract)；code generation(abstract)；分类 cs.SE、cs.AI

Out of Context: How important is Local Context in Neural Program Repair?

Julian Aron Prenner, Romain Robbes

专题命中 程序修复 ：program repair(title,abstract)；code model(abstract)；分类 cs.SE、cs.AI

Dynamic Neural Program Embedding for Program Repair

Ke Wang, Rishabh Singh, Zhendong Su

专题命中 程序修复 ：program repair(title,abstract)；program synthesis(abstract)；分类 cs.AI、cs.PL

Comments 9 pages

Refine After Generation: Toward Correct and Concise Patches in LLM-based Program Repair

生成后优化：面向基于大语言模型的程序修复中正确且简洁的补丁

Wenqiang Luo, Jacky Keung, Xiaoyu Shi, Yicheng Sun, Boyang Yang, Zhou Yang, Haoye Tian

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE

AI总结 针对基于LLM的程序修复中补丁冗余问题，提出RECAP适配器，在保留或提升解决率的同时，大幅降低补丁大小，实现更优的大小-正确性权衡。

Bug Report Specification Refinement with Trajectory Guidance for Automated Program Repair

基于轨迹引导的自动程序修复的错误报告规范细化

S M Farah Al Fahim, Md Nakhla Rafi, Md Ahasanuzzaman, Zeyang Ma, Dong Jae Kim, Shaowei Wang, Tse-Hsun, Chen

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE

AI总结 研究针对自动程序修复中错误报告规范不完善的问题，提出TrajSpec方法，通过轨迹引导收集证据并组织成三级表示，经审查生成细化报告，实验表明该方法能有效提高修复性能。

EviACT: An Evidence-to-Action Framework for Agentic Program Repair

EviACT：一种面向智能体程序修复的证据到行动框架

Qianru Meng, Xiao Zhang, Zhaochun Ren, Joost Visser

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE

AI总结 提出EviACT框架，通过协调三个证据驱动的防护栏（检索支架、编译门、测试驱动门）来提升智能体程序修复的定位、生成和验证效率，在多个基准上修复率提升1.6-6.0个百分点，API成本降低70.1-88.6%。

CI-Repair-Bench: A Repository-Aware Benchmark for Automated Patch Validation via CI Workflows

CI-Repair-Bench：基于CI工作流的自动化补丁验证仓库意识基准

Rabeya Khatun Muna, Md Nakhla Rafi, Tse-Hsun, Chen

专题命中 程序修复 ：repository(title,abstract)；program repair(abstract)；分类 cs.SE

AI总结 CI-Repair-Bench通过真实GitHub Actions执行构建，提供仓库级程序修复基准，包含567个CI失败实例，细粒度评估12种CI错误类型，揭示自动化修复在局部和工具强制失败上效果最佳，但环境依赖等问题仍具挑战。

GALA: Multimodal Graph Alignment for Bug Localization in Automated Program Repair

GALA: 多模态图对齐用于自动化程序修复中的缺陷定位

Zhuoyao Liu, Zhengran Zeng, Shu-Dong Huang, Yang Liu, Shikun Zhang, Wei Ye

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE

AI总结 GALA通过多模态图对齐方法，解决GUI截图场景下自动化程序修复的缺陷定位问题，通过结构化推理提升视觉与代码的映射精度。

Comments Code available at: https://github.com/lzyyyyy666/GALA

Hierarchical Knowledge Injection for Improving LLM-based Program Repair

分层知识注入以提高基于LLM的程序修复

Ramtin Ehsani, Esteban Parra, Sonia Haiduc, Preetha Chatterjee

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE

AI总结 本文提出分层知识注入框架，通过逐步提供结构化上下文提高LLM在程序修复中的表现，实现79%的修复率，展示不同bug类型对上下文层次的需求差异。

Comments Accepted at IEEE/ACM Automated Software Engineering (ASE) 2025 Conference

Journal ref Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2025, pp. 1440-1452

Reasoning Distillation for Lightweight Automated Program Repair

轻量级自动程序修复中的推理蒸馏

Aanand Balasubramanian, Sashank Silwal

机构 * Purdue University（普渡大学） 纠错

专题命中 程序修复 ：program repair(title,abstract)；code model(abstract)；分类 cs.LG

AI总结 本文提出通过符号推理蒸馏提升轻量级自动程序修复模型的可解释性和鲁棒性。

Comments 8 pages, 5 tables. Preprint

Input Reduction Enhanced LLM-based Program Repair

输入减少增强的基于大语言模型的程序修复

Boyang Yang, Luyao Ren, Xin Yin, Jiadong Ren, Haoye Tian, Shunfu Jin

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE

AI总结 本研究提出ReduceFix方法，通过减少故障诱导输入提升基于LLM的程序修复性能，实验表明其在多个基准上显著提高了修复准确率。

REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement

Anvith Pabba, Simin Chen, Alex Mathai, Anindya Chakraborty, Baishakhi Ray

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE

Comments We also open source our code at https://anonymous.4open.science/r/SemAgent-7B2F/README.md

Towards Speeding up Program Repair with Non-Autoregressive Model

Zhenyu Yang, Yue Pan, Zhen Yang, Zhongxing Yu

专题命中 程序修复 ：program repair(title,abstract)；code generation(abstract)；分类 cs.SE

Comments 30 pages, 8 figures, 7 tables. arXiv admin note: substantial text overlap with arXiv:2406.16526

The Impact of Fine-tuning Large Language Models on Automated Program Repair

Roman Macháček, Anastasiia Grishina, Max Hort, Leon Moonen

机构 * Simula Research Laboratory（Simula研究实验室） ； University of Bern（伯尔尼大学） 纠错

专题命中 程序修复 ：program repair(title,abstract)；分类 cs.SE、cs.CL、cs.AI

Comments Accepted for publication in the research track of the 41th International Conference on Software Maintenance and Evolution (ICSME 2025)

The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models

Fernando Vallecillos Ruiz, Max Hort, Leon Moonen

机构 * Simula Research Laboratory（Simula研究实验室） 纠错

专题命中 程序修复 ：program repair(title,abstract)；分类 cs.SE、cs.CL、cs.AI

Comments Accepted for publication in the research track of the 29th International Conference on Evaluation and Assessment in Software Engineering (EASE), 17-20 June 2025, Istanbul, Türkiye

Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning

Chunqiu Steven Xia, Lingming Zhang

专题命中 程序修复 ：program repair(title,abstract)；code model(abstract)；分类 cs.SE

Comments Accepted at ESEC/FSE 2022

Journal ref ESEC/FSE 2022: Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering

Revisiting Evolutionary Program Repair via Code Language Model

Yunan Wang, Tingyu Guo, Zilong Huang, Yuan Yuan

专题命中 程序修复 ：program repair(title,abstract)；code generation(abstract)；分类 cs.SE

Search-based Automated Program Repair of CPS Controllers Modeled in Simulink-Stateflow

Aitor Arrieta, Pablo Valle, Shaukat Ali

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE

GAMMA: Revisiting Template-based Automated Program Repair via Mask Prediction

Quanjun Zhang, Chunrong Fang, Tongke Zhang, Bowen Yu, Weisong Sun, Zhenyu Chen

专题命中 程序修复 ：program repair(title,abstract)；code generation(abstract)；分类 cs.SE

Comments Accepted to 38th IEEE/ACM International Conference on Automated Software Engineering (ASE2023)

A study on Prompt Design, Advantages and Limitations of ChatGPT for Deep Learning Program Repair

Jialun Cao, Meiziniu Li, Ming Wen, Shing-chi Cheung

专题命中 程序修复 ：program repair(title,abstract)；code generation(abstract)；分类 cs.SE

Comments 10 pages

Estimating the Potential of Program Repair Search Spaces with Commit Analysis

Khashayar Etemadi, Niloofar Tarighat, Siddharth Yadav, Matias Martinez, Martin Monperrus

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE

Journal ref Journal of Systems and Software, 2022

Bears: An Extensible Java Bug Benchmark for Automatic Program Repair Studies

Fernanda Madeiral, Simon Urli, Marcelo Maia, Martin Monperrus

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE

Comments Proceedings of the 26th IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER '19)

Journal ref Proceedings of the 26th IEEE International Conference on Software Analysis, Evolution and Reengineering, 2019