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. From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving

    Aug 14, 2026Dipankar SarkarNeuro-Symbolic ReasoningLLM-Based Program Synthesis

    Independent Researcher

  2. Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency

    Aug 14, 2026Junchi Liu, Ali Bigdeli, Roya Daneshi +3Automated Program RepairLLM Inference Efficiency

    Colorado State University, United States

  3. Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test

    Aug 13, 2026Saveliy BatruinAutomated Program RepairSheaf Theory

    Independent researcher

  4. Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations

    Aug 10, 2026Weijie Liang, Yuanfeng Song, Xing Chen +3Automated Program RepairAI Coding Agents

    The Hong Kong University of Science and Technology, Hong Kong, China · ByteDance, China

  5. CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training

    Aug 6, 2026Amine Lbath, Manan Suri, Aurelien Delaitre +4Automated Program RepairSoftware Vulnerability Detection

    National Institute of Standards and Technology · Université Grenoble Alpes, CNRS · University of Maryland, College Park

  6. Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports

    Aug 5, 2026Haobin Li, Ping Deng, Weizhong Qian +4Automated Program RepairAI Coding Agents

    Sichuan University · University of Electronic Science and Technology of China · Independent Researchers

  7. TraceCAD: Trace-Guided Repair for Agentic CAD Generation

    Aug 4, 2026Fengxiao Fan, Jingzhe Ni, Fan Sang +5Automated Program RepairParametric CAD Modeling

    Zhejiang University, China

  8. Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Accelerator Kernels

    Aug 3, 2026Yansong Sun, Shenxiu Wu, Siyuan Chen +6Automated Program RepairGPU Kernel Generation

    Department of Computer Science, City University of Hong Kong · Application Software Engineering Lab, Huawei Technologies Ltd.

  9. RefactorAssist: Agentic Refinement for Reliable Code Refactoring

    Aug 2, 2026Jonathan Cordeiro, Shayan Noei, Ying ZouLLM Self-RefinementAutomated Program Repair

    Queen’s University, Kingston, Canada

  10. TaPR: Test-Aware Policy Refinement for Feedback-Conditioned Code Generation

    Aug 1, 2026Aofan Liu, Jingxiang Meng, Fangxin Liu +1RL for Code GenerationReward Shaping

    ∗These authors contributed equally. · †Corresponding author.

  11. AgenticRepair: Multi-Faceted Program Context Engineering for Agentic Vulnerability Repair

    Jul 31, 2026Michael Fu, Qiyue Mei, Patanamon Thongtanunam +1Automated Program RepairAgentic Code Generation

    the School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia. · Kla Tantithamthavorn is with the Faculty of Information Technology, Monash University, Melbourne, Australia.

  12. Open-Source LLM-Driven Formal Verification: A Multi-Agent Pipeline for RTL Repair

    Jul 30, 2026Ha Trung TranFormal Hardware VerificationAutomated Program Repair

    Independent Researcher · Seattle, WA, USA

  13. Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?

    Jul 30, 2026Xiaonan Xu, Wenjing WuAutomated Software TestingAutomated Program Repair

    College of Computing, Georgia Institute of Technology, Atlanta, GA, 30332, USA. · Department of Computer Science, University of Colorado Boulder, Boulder, CO, 80309, USA.

  14. Does Runtime Topology Context Improve LLM-Generated Kubernetes Security Patches?

    Jul 28, 2026Farooq ShaikhAutomated Program RepairLLM Prompting

    Dynatrace Research, Linz, Austria

  15. How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair

    Jul 28, 2026Ramtin Ehsani, Irene Manotas, Saurabh Pujar +2Automated Program RepairLLM Interpretability

    Drexel University Philadelphia, PA, USA · IBM Research Yorktown, NY, USA

  16. Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair

    Jul 27, 2026Xueping Gao, Jianwei Yang, Qiang YangAgent Failure AnalysisLLM Self-Correction

    Alibaba Cloud Computing Hangzhou, China

  17. Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes

    Jul 22, 2026Yuhao Tan, Zhibang Yang, Fangkai Yang +9Automated Software TestingAutomated Program Repair

    1Nanjing University · 2Peking University · 3Microsoft

  18. Tool-Guided Retrieval-Augmented Repair for Securing LLM-Generated C Code

    Jul 21, 2026Vidyut Sriram, Saatvik Pradhan, Suman SahaAutomated Program RepairCode Generation

    The Pennsylvania State University

  19. PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents

    Jul 21, 2026Tianyue Jiang, Yanlin Wang, Xin He +7LLM Self-CorrectionSoftware Engineering Agents

    Sun Yat-sen University, China · State Key Laboratory of Blockchain and Data Security, Zhejiang University, China · School of Cyber Science and Engineering, Huazhong University of Science and Technology, China +1

  20. Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models

    Jul 14, 2026Mehmet IscanLLM Self-CorrectionAutomated Program Repair

    PythaLab, Yıldız Technical University, Istanbul, Turkey

  21. Bulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities

    Jul 14, 2026Qiyuan Fan, Zhi Li, Junjie Li +3Automated Program RepairSoftware Vulnerability Detection

    Huazhong University of Science and Technology, Wuhan, China · Nanyang Technological University, Singapore

  22. Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs

    Jul 14, 2026Zhili Huang, Ling Xu, Hongyu ZhangAutomated Program Repair

    Chongqing University, Chongqing, China

  23. SmartHomeSecure: Automated Detection and Repair of Smart Home Configuration Errors Using Large Language Models

    Jul 7, 2026Yizhi Wang, Xinghua Gao, Reachsak Ly +1Automated Program RepairInternet of Things

    Myers-Lawson School of Construction, Virginia Polytechnic Institute and State University, Blacksburg, VA 24061, USA · School of Technology, Eastern Illinois University, Charleston, Illinois, United States

  24. Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse

    Jul 5, 2026Raj Jaiswal, Anany Singh Divy, Savar Bhasin +3LLM Self-CorrectionAutomated Program Repair

    IIIT Delhi · Microsoft Research India · IIT Kanpur

  25. Anchored Self-Play for Code Repair

    Jul 3, 2026Caroline Choi, Zeyneb Kaya, Shirley Wu +3RL for Code GenerationAutomated Program Repair

    Department of Computer Science, Stanford University, Stanford, CA, USA.

  26. ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair

    Jul 2, 2026Chiwang Luk, Matin Mohammad Najafi, Zhifeng Jia +6Automated Program RepairAI Coding Agents

    Huawei · HKUST(GZ) · Nanyang Technological University

  27. SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests

    Jul 1, 2026Yaoqi Guo, Yang Liu, Jie M. Zhang +3Software Engineering AgentsAutomated Program Repair

    Nanyang Technology University · King’s College London · Peking University +2

  28. LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution

    Jul 1, 2026Zhao Tian, Yingquan Zhao, Chenyao Suo +2LLM EvaluationAutomated Program Repair

    School of Computer Software, Tianjin University, Tianjin, China · School of Cybersecurity, Tianjin University, Tianjin, China · School of Computer Science, University of Bristol, Bristol, UK

  29. Calibration, Not Compilation: Detecting and Repairing Misspecified Probabilistic Programs Written by Language Models

    Jun 30, 2026Jian Xu, Delu Zeng, John Paisley +1Automated Program RepairBayesian Inference

    RIKEN iTHEMS · RIKEN AIP · South China University of Technology +1

  30. Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models

    Jun 30, 2026Mehmet IscanLLM Self-CorrectionAutomated Program Repair

    PythaLab, Yıldız Technical University, Istanbul, Turkey