代码大模型 / AI 编程

PAFT: Preservation Aware Fine-Tuning for Minimal-Edit Program Repair

PAFT：面向最小编辑程序修复的保留意识微调

Boyang Yang, Zijian Cai, Shunfu Jin, Haoye Tian

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

AI总结 PAFT通过保留意识微调方法，在Defects4J和HumanEval-Java上将pass@1提升65.6%，同时降低平均编辑距离32.6%，实现更小、更局部化的合理补丁。

ComPass: Contrastive Learning for Automated Patch Correctness Assessment in Program Repair

ComPass：基于对比学习的程序修复中自动补丁正确性评估

Quanjun Zhang, Ye Shang, Haichuan Hu, Chunrong Fang, Zhenyu Chen, Liang Xiao

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

AI总结 ComPass利用对比学习和数据增强解决程序修复中补丁过拟合问题，通过代码转换规则生成语义保持的代码片段，提升补丁正确性评估的准确性。

Comments 31 pages, 3 figures

DebugHarness: Emulating Human Dynamic Debugging for Autonomous Program Repair

DebugHarness: 模拟人类动态调试以实现自主程序修复

Maolin Sun, Yibiao Yang, Xuanlin Liu, Yuming Zhou, Baowen Xu

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

AI总结 DebugHarness通过模拟人类动态调试过程，利用LLM实现复杂漏洞的自动修复，其动态调试方法在SEC-bench数据集上实现了90%的修复率，比现有方法提升30%以上。

Comments 15 pages, 6 figures

Semantic Evolution over Populations for LLM-Guided Automated Program Repair

基于种群的语义进化用于LLM引导的自动程序修复

Cuong Chi Le, Minh Le-Anh, Cuong Duc Van, Tien N. Nguyen

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

AI总结 本文提出EvolRepair框架，通过语义进化算法提升LLM引导的自动程序修复效果，解决修复假设多样性、语义相关修复家族识别等挑战。

Exploring Generalizable Automated Program Repair with Large Language Models

探索大型语言模型在通用自动程序修复中的应用

Viola Campos, Ridwan Shariffdeen, Adrian Ulges, Yannic Noller

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

AI总结 本文探讨了大型语言模型在自动程序修复中的应用，发现不同模型在不同语言上表现各异，需结合多个模型以提高修复效果，并指出故障定位的不完美会显著影响修复准确性。

A Systematic Literature Review on Large Language Models for Automated Program Repair

基于大型语言模型的自动程序修复系统文献综述

Quanjun Zhang, Chunrong Fang, Yang Xie, YuXiang Ma, Weisong Sun, Yun Yang, Zhenyu Chen

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

AI总结 本文系统综述了2020-2025年间基于大型语言模型的自动程序修复技术，分析了其应用、挑战与未来方向。

Comments Accepted to ACM Transactions on Software Engineering and Methodology (TOSEM 2026)

Specification Vibing for Automated Program Repair

基于规范的自动化程序修复

Taohong Zhu, Lucas C. Cordeiro, Mustafa A. Mustafa, Youcheng Sun

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

AI总结 VibeRepair通过行为规范修复替代传统代码编辑，提升自动化程序修复的准确性和泛化能力。

RGFL: Reasoning Guided Fault Localization for Automated Program Repair Using Large Language Models

RGFL：基于大语言模型的自动化程序修复中的推理引导故障定位

Melika Sepidband, Hamed Taherkhani, Hung Viet Pham, Hadi Hemmati

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

AI总结 RGFL通过引入分层推理模块和反事实分析，提升自动化程序修复中的文件和元素级故障定位精度，显著提高修复成功率。

Comments 23 pages, 5 figures

A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications

基于大型语言模型的自动程序修复综述：分类、设计范式与应用

Boyang Yang, Zijian Cai, Fengling Liu, Bach Le, Lingming Zhang, Tegawendé F. Bissyandé, Yang Liu, Haoye Tian

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

AI总结 本文综述了基于LLM的自动程序修复，提出统一分类法，涵盖四种范式，并讨论了评估实践和未来研究方向。

Summary-Mediated Repair: Can LLMs use code summarisation as a tool for program repair?

基于摘要的修复：大语言模型能否将代码摘要作为程序修复工具？

Lukas Twist

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

AI总结 本研究提出基于摘要的程序修复方法，利用代码摘要作为中间步骤，通过提升修复效果来改进大语言模型在程序修复中的表现。

Comments 6 pages, 3 tables, 1 figure

Enhancing Automated Program Repair via Faulty Token Localization and Quality-Aware Patch Refinement

通过故障性令牌定位和质量感知补丁细化增强自动程序修复

Jiaolong Kong, Xiaofei Xie, Yiheng Xiong, Yuekun Wang, Jian Wang

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

AI总结 TokenRepair通过内部反思定位潜在故障令牌并结合质量感知的外部反馈，提升自动程序修复的效率和准确性。

ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs

ContrastRepair: 通过对比测试用例对增强基于对话的自动程序修复

Jiaolong Kong, Mingfei Cheng, Xiaofei Xie, Shangqing Liu, Xiaoning Du, Qi Guo

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

AI总结 ContrastRepair通过对比测试对提升基于对话的自动程序修复效果，显著优于现有方法。

Journal ref ACM Trans. Softw. Eng. Methodol., 34(8), Article 216, 2025

Rethinking Kernel Program Repair: Benchmarking and Enhancing LLMs with RGym

重新思考内核程序修复：通过RGym基准测试和增强LLMs

Kareem Shehada, Yifan Wu, Wyatt D. Feng, Adithya Iyer, Gryphon Kumfert, Yangruibo Ding, Zhiyun Qian

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

AI总结 本研究提出RGym框架，通过改进的定位技术和提示结构，提升LLMs在Linux内核程序修复中的性能和效率。

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling

PathFix: Automated Program Repair with Expected Path

Xu He, Shu Wang, Kun Sun

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

Comments This is the author's version of a paper accepted at SecDev 2025 (IEEE)

Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities

Simin Chen, Yixin He, Suman Jana, Baishakhi Ray

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

WARP -- Web-Augmented Real-time Program Repairer: A Real-Time Compilation Error Resolution using LLMs and Web-Augmented Synthesis

Anderson de Lima Luiz

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

Comments 5 pages, 2 figures

RelRepair: Enhancing Automated Program Repair by Retrieving Relevant Code

Shunyu Liu, Guangdong Bai, Mark Utting, Guowei Yang

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

Comments 11 pages, 5 figures, under review at TSE

Boosting Redundancy-based Automated Program Repair by Fine-grained Pattern Mining

Jiajun Jiang, Fengjie Li, Zijie Zhao, Zhirui Ye, Mengjiao Liu, Bo Wang, Hongyu Zhang, Junjie Chen

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

Comments This paper has been accepted by ICSME 2025

On the need to perform comprehensive evaluations of automated program repair benchmarks: Sorald case study

Sumudu Liyanage, Sherlock A. Licorish, Markus Wagner, Stephen G. MacDonell

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

Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models

Hanyang Guo, Xiaoheng Xie, Hong-Ning Dai, Peng Di, Yu Zhang, Bishenghui Tao, Zibin Zheng

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

Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair via Repair Ingredients Search

Jiayi Zhang, Kai Huang, Jian Zhang, Yang Liu, Chunyang Chen

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

Comments Accepted by ICSE 2026. Jiayi Zhang and Kai Huang contributed equally to this work

Empirical Evaluation of Large Language Models in Automated Program Repair

Jiajun Sun, Fengjie Li, Xinzhu Qi, Hongyu Zhang, Jiajun Jiang

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

Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning

Xunzhu Tang, Jacques Klein, Tegawendé F. Bissyandé

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

Fixing 7,400 Bugs for 1$: Cheap Crash-Site Program Repair

Han Zheng, Ilia Shumailov, Tianqi Fan, Aiden Hall, Mathias Payer

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

Adapting Knowledge Prompt Tuning for Enhanced Automated Program Repair

Xuemeng Cai, Lingxiao Jiang

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

Exploring and Lifting the Robustness of LLM-powered Automated Program Repair with Metamorphic Testing

Pengyu Xue, Linhao Wu, Zhen Yang, Zhongxing Yu, Zhi Jin, Ge Li, Yan Xiao, Shuo Liu, Xinyi Li, Hongyi Lin, Jingwen Wu

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

Show Me Why It's Correct: Saving 1/3 of Debugging Time in Program Repair with Interactive Runtime Comparison

Ruixin Wang, Zhongkai Zhao, Le Fang, Nan Jiang, Yiling Lou, Lin Tan, Tianyi Zhang

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

Comments 27 pages, 8 figures, OOPSLA 2025

Journal ref Proc. ACM Program. Lang. 9, OOPSLA1, Article 145 (April 2025)

Knowledge-Enhanced Program Repair for Data Science Code

Shuyin Ouyang, Jie M. Zhang, Zeyu Sun, Albert Merono Penuela

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

Journal ref ICSE 2025

Practical Program Repair in the Era of Large Pre-trained Language Models

Chunqiu Steven Xia, Yuxiang Wei, Lingming Zhang

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

Journal ref ICSE 2023: Proceedings of the 45th International Conference on Software Engineering

When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair

Wenqiang Luo, Jacky Wai Keung, Boyang Yang, He Ye, Claire Le Goues, Tegawende F. Bissyande, Haoye Tian, Bach Le

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