Automated Program Repair

Follow this topic Ask about this topic

Automated program repair studies how to find and correct bugs while preserving a program’s intended behavior. Approaches range from search-based patch generation and program analysis to language models that use fault localization, repository context, retrieved examples, and iterative agent workflows. Tests, runtime traces, static analysis, and formal methods can guide or verify repairs, with benchmarks spanning small functions, repositories such as those tested by SWE-bench, and security or hardware code. A central challenge is that compiling or passing available tests does not guarantee a secure, semantically correct, minimal fix, so stronger oracles must be balanced against context limits, cost, and generalization.

Latest papers

158 papers32 papers in the last four weeks, up 68% on the four weeks before. 0.2% of all new papers.

RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair
Mar 1, 2026Zhongqiang Pan, Chuanyi Li, Wenkang Zhong +3Repository-Level Program Repair Automated Program Repair
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · Human Language Technology Research Institute, University of Texas at Dallas, Richardson, Texas, USA
SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks
Feb 28, 2026Yucheng Zeng, Shupeng Li, Daxiang Dong +11Synthetic Benchmark Generation Software Engineering Benchmarks
Qianfan Team, Baidu Inc.
SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents
Feb 25, 2026Patrick Tser Jern Kon, Archana Pradeep, Ang Chen +5Software Engineering Agents Small Language Models
University of Michigan · Meta · Stanford University
Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?
Feb 20, 2026Spandan Garg, Yufan HuangCoding Agents Automated Program Repair
Microsoft USA
The Limits of Long-Context Reasoning in Automated Bug Fixing
Feb 17, 2026Ravi Raju, Mengmeng Ji, Shubhangi Upasani +2Long-Context Reasoning in Language Models Long-Context Language Model Evaluation
SambaNova Systems San Jose, CA 95134, USA
HAFixAgent: History-Aware Agentic Program Repair
Nov 2, 2025Yu Shi, Hao Li, Bram Adams +1Automated Program Repair Software Engineering Agents
Queen’s University, Kingston, Canada
From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs
Jun 16, 2025Anh Ho, Thanh Le-Cong, Bach Le +1Automated Program Repair Software Engineering Benchmarks
The University of Melbourne, Australia · Singapore University of Technology and Design, Singapore
kAgent: An execution-guided crash resolution agent for the Linux kernel
Apr 29, 2025Alex Mathai, Chenxi Huang, Suwei Ma +7Software Engineering Agents Automated Program Repair
Department of Computer Science, Columbia University, New York, NY, USA · Google Inc., München, Germany · Google DeepMind, Mountain View, CA, USA +1

Mar 1, 2026J/K move · Enter open · S save

RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair

Zhongqiang Pan, Chuanyi Li, Wenkang Zhong, Yi Feng+2

State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · Human Language Technology Research Institute, University of Texas at Dallas, Richardson, Texas, USA

Repository-Level Program Repair Automated Program Repair Fault Localization

Open paper AskPDF arXiv

Automated program repair (APR) struggles to scale from isolated functions to full repositories, as it demands a global, task-aware understanding to locate necessary changes. Current methods, limited by context and reliant on shallow retrieval or costly agent iterations, falter on complex cross-file issues. To this end, we propose RepoRepair, a novel documentation-enhanced approach for repository-level fault localization and program repair. Our core insight is to leverage LLMs to generate hierarchical code documentation (from functions to files) for code repositories, creating structured semantic abstractions that enable LLMs to comprehend repository-level context and dependencies. Specifically, RepoRepair first employs a text-based LLM (e.g., DeepSeek-V3) to generate file/function-level code documentation for repositories, which serves as auxiliary knowledge to guide fault localization. Subsequently, based on the fault localization results and the issue description, a powerful LLM (e.g., Claude-4) attempts to repair the identified suspicious code snippets. Evaluated on SWE-bench Lite, RepoRepair achieves a 45.7% repair rate at a low cost of

0.44 per fix. On SWE-bench Multimodal, it delivers state-of-the-art performance with a 37.1% repair rate despite a higher cost of

0.56 per fix, demonstrating robust and cost-effective performance across diverse problem domains.