Automated Program Repair

Ask about this topic

Overview

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

CardsList

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

  1. RegoMender: A Multi-agent Framework for Automated Rego Policy Repair

    Oct 21, 2026Ruijie Zhang, Huaxiao Yin, Li Hu +5Automated Program Repair

    Institute of Information Engineering, Chinese Academy of Sciences Beijing, China School of Cyber Security, University of Chinese Academy of Sciences Beijing, China · University of Science and Technology of China Hefei, China · Peking University Beijing, China +2

  2. Where Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time Resources

    Oct 20, 2026Saiyue Lyu, Jerrold Huang, Yunbei Zhang +4Inference-Time Compute AllocationSoftware Engineering Agents

    University of British Columbia · University of Toronto · Tulane University +2

  3. What Do RTL Repair Benchmarks Actually Measure?

    Oct 20, 2026Yeyin Eva Zhu, Rishabh RanawatAutomated Program RepairLLM Evaluation

    Independent

  4. RELAY: Scaling Historical Build Restoration through Rule Reuse and Agentic Repair

    Oct 20, 2026Olivier Nourry, Yoshiki HigoSoftware Engineering AgentsAutomated Program Repair

    The University of Osaka, Osaka, Japan

  5. Fix, Not Just Resample: Bounded Compiler-Guided Repair in Lean 4

    Oct 18, 2026Haotian Deng, Chris Farber, Sonal Narasimha +2Automated Theorem ProvingLarge Language Model-Guided Theorem Proving

    Purdue University

  6. Teaching Code Agents to Ask Without Leaking Private Code

    Oct 17, 2026Wenjia Jiang, Jieke Shi, Zhensu Sun +9AI Coding AgentsPrivacy Protection for LLM Agents

    Singapore Management University · University of Alberta · Alberta Machine Intelligence Institute (Amii) +6

  7. SCOPE: Selective Certification of Program Edits for Embodied Heuristic Learning

    Oct 16, 2026Junyang Shu, Bingqing Wei, Jishuo Li +2Automated Program Repair

    Wangxuan Institute of Computer Technology, Peking University, China · Beijing Academy of Artificial Intelligence · VGI Labs

  8. MemScope: Evolving Agent Memory Architectures through Localized Code Repair

    Oct 15, 2026Miao Su, Yucan Guo, Zixuan Li +4LLM Agent MemorySelf-Evolving Agents

    State Key Laboratory of AI Safety · Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences +1

  9. P2Patch: Exploit-Guided Vulnerability Repair

    Oct 14, 2026Mohsen Iranmanesh, Sina Moradi Sabet, Sina Marefat +7Automated Exploit GenerationAutomated Program Repair

    Simon Fraser University, Canada · Amirkabir University of Technology, Iran · K. N. Toosi University of Technology, Iran +1

  10. JevCoder: When Does Decision Delegation Pay Off in Code Repair?

    Oct 14, 2026Jiahao Zhang, Yifan Zhang, Yu HuangAutomated Program RepairCoding Agents

    Vanderbilt University, Nashville, Tennessee, USA

  11. PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards

    Oct 13, 2026Yunkai Zhan, Miaosen Chai, Shangshang Wang +5Automated Program RepairRL Post-Training

    University of Southern California · University of Chicago · Google +1

  12. SWEPatchTest: Evaluating Software Tests Beyond Reproduction

    Oct 13, 2026Hua Lu, Pengcheng Wang, Han Li +4Software Engineering BenchmarksAutomated Test Generation

    Baidu Inc. · Nanjing University · The Chinese University of Hong Kong

  13. CWE-bench: Refocusing Agentic Security from Exploitation to Defense

    Oct 12, 2026Gonzalo Gonzalez-Pumariega, Ajay Jagannath, Adit Jain +3AI Agent SecurityAI Agent Security Benchmarks

  14. RoboBugBench: Benchmarking Automated Repair of Real Robot Software Under an Audited Behavioral Oracle

    Oct 12, 2026Alexey TuzikovAutomated Program Repair

    Robouley · Stanford University

  15. Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair

    Oct 11, 2026Elad Sharony, Ido Greenberg, Jialin Song +3Automated Program Repair

    Technion · NVIDIA

  16. VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs

    Oct 9, 2026Fuqiang Wang, Zheng Guo, Xiaoming Wu +53D Scene Layout GenerationLLM-Based Program Synthesis

    Qilu University of Technology, Jinan, China · Tianjin University, Tianjin, China · Shandong University, Jinan, China +3

  17. VETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics Reasoning

    Oct 9, 2026Yingbo Ma, Kuangshi Ai, Gordon Dai +3LLM Self-RefinementAutomated Program Repair

    New York University · University of Notre Dame

  18. SWE-Duel: Towards a Self-Scaling Arena for Coding Agents

    Oct 8, 2026Wei Minn, Zhensu Sun, Lwin Khin Shar +1Benchmark DesignCoding Agents

    School of Computing and Information Systems Singapore Management University

  19. Beyond the Leaderboard: Multi-Dimensional Evaluation of Dense and Mixture-of-Experts Models for Automated Program Repair

    Oct 6, 2026Anvi Kalpesh Shah, Umamaheswara Sharma BSoftware EngineeringAutomated Program Repair

    National Institute of Technology, Calicut

  20. Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google Scale

    Oct 5, 2026Celal Ziftci, Spencer Greene, Ray Liu +2Automated Program RepairSoftware Engineering

    Google New York, USA

  21. Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks

    Oct 5, 2026Tobias Heldt, Matt Turk, Christoph Landolt +1Automated Exploit GenerationAutomated Program Repair

    XOR · Protege · CISPA Helmholtz Center for Information Security

  22. Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair

    Oct 5, 2026Wenji Bai, Muhammad Waseem, Zeeshan Rasheed +2Agent Failure AnalysisAutomated Program Repair

    Tampere University, Tampere, Finland

  23. TeleGen: Improving LLM-Based Web Application Generation via Runtime Telemetry

    Oct 4, 2026Yujia Luo, Haonan Zhang, Jiasi Shen +2Web Application GenerationExecution-Guided Code Generation

    The Hong Kong University of Science and Technology (Guangzhou) · University of Waterloo · The Hong Kong University of Science and Technology

  24. AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems

    Oct 3, 2026Muhammad Bilal Awan, Zubair Hussain, Abdul ShahidAgentic WorkflowsAutomated Program Repair

    Ministry of Defense, Doha, Qatar · IQRA University, Islamabad, Pakistan · South East Technological University, Waterford, Ireland

  25. RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair

    Oct 3, 2026Rabeya Khatun Muna, Muhammad Ahasanuzzaman, Nakhla Rafi +3Automated Program RepairRetrieval-Augmented ICL

    Software Performance, Analysis, and Reliability (SPEAR) Lab, Concordia University · Concordia University

  26. SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown

    Oct 2, 2026Yuxuan Liu, Haoran Li, Yuhao Zhang +10AI Agent BenchmarksLLM Agent Self-Improvement

    The Hong Kong University of Science and Technology · Harbin Institute of Technology, Shenzhen, China · Harbin Institute of Technology, Harbin, China

  27. Teaching Agents to Code Reliably

    Oct 2, 2026Muhammad Ahmed Mohsin, Myeongsoo Kim, Kangrui Ruan +3Repository-Level Program RepairAI Coding Agents

    Stanford University · AWS AI Labs

  28. An Executable Benchmark for LLM-Based HLS Repair:Design Complexity and Repair Underconstraint

    Oct 2, 2026Maisha Mastora, Dean SullivanAutomated Program RepairElectronic Design Automation

    Department of Electrical and Computer Engineering University of New Hampshire Durham, NH, USA

  29. Trustworthy Runtime Error Healing in Real-World Repositories: A Benchmark and Guardrail

    Sep 30, 2026Gou Tan, Pengfei Chen, Zhensu Sun +9Automated Program RepairLLM Guardrails

    Sun Yat-sen University · Singapore Management University · Monash University

  30. Rules to Tools: Executable Checks for LLM Agents in Scientific Computing

    Sep 29, 2026Jingjie Ning, Guojiang Zhao, Chen Xu +4Automated Program RepairTool-Using Agents

    School of Computer Science, Carnegie Mellon University · DP Technology