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

159 papers33 papers in the last four weeks, up 74% on the four weeks before. 0.2% of all new papers.

  1. Understanding Scattered Forest Search: A Version-Space Perspective on Multi-Turn Program Correction

    Apr 27, 2026Yuto Tanaka, Issei SatoAutomated Program RepairMonte Carlo Tree Search

    Department of Computer Science The University of Tokyo Tokyo, Japan

  2. A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair

    Apr 23, 2026Milan De Koning, Ali Asgari, Pouria Derakhshanfar +1LLM EvaluationMetamorphic Testing

    JetBrains Research, Amsterdam, The Netherlands · Delft University of Technology, Delft, The Netherlands

  3. Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs

    Apr 22, 2026He Yang Yuan, Xin Wang, Kundi Yao +3Automated Program RepairSoftware Vulnerability Detection

    York University, Toronto, Canada · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · University of Waterloo, Waterloo, Canada +1

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

    Apr 19, 2026Yongchao Wang, Zhiqiu HuangSoftware Engineering AgentsAutomated Program Repair

    Nanjing University of Aeronautics and Astronautics

  5. Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?

    Apr 19, 2026Miaosen Chai, Wang Bill Zhu, Shangshang Wang +5LLM EvaluationAutomated Program Repair

    University of Southern California · Microsoft · University of Wisconsin–Madison +1

  6. Clover: A Neural-Symbolic Agentic Harness with Stochastic Tree-of-Thoughts for Verified RTL Repair

    Apr 19, 2026Zizhang Luo, Yansong Xu, Runlin Guo +6Automated Program RepairTree of Thoughts

    Peking University

  7. SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair

    Apr 19, 2026Yifan Zhang, Jieyu Li, Kexin Pei +2Automated Program RepairNeuro-Symbolic AI

    Vanderbilt University1 · University of Chicago2

  8. HWE-Bench: Benchmarking LLM Agents on Real-World Hardware Bug Repair Tasks

    Apr 16, 2026Fan Cui, Hongyuan Hou, Zizhang Luo +2Automated Program RepairElectronic Design Automation

    Peking University · Beijing, China

  9. LogicEval: A Systematic Framework for Evaluating Automated Repair Techniques for Logical Vulnerabilities in Real-World Software

    Apr 14, 2026Syed Md Mukit Rashid, Abdullah Al Ishtiaq, Kai Tu +7Automated Program RepairSoftware Security

    The Pennsylvania State University

  10. Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis

    Apr 12, 2026Jugal GajjarSoftware Vulnerability DetectionLLMs for Cybersecurity

    Department of Computer Science, The George Washington University, Washington, DC 20052

  11. The Code Whisperer: LLM and Graph-Based AI for Smell and Vulnerability Resolution

    Apr 12, 2026Mohammad Baqar, Raji Rustamov, Alexander HughesSoftware Vulnerability DetectionStatic Code Analysis

  12. How Many Tries Does It Take? Iterative Self-Repair in LLM Code Generation Across Model Scales and Benchmarks

    Apr 12, 2026Johin Johny ArimburLLM Self-CorrectionLLM Code Generation

    Independent Researcher

  13. PatchRecall: Patch-Driven Retrieval for Automated Program Repair

    Apr 12, 2026Mahir Labib Dihan, Faria Binta Awal, Md. Ishrak AhsanAutomated Program RepairHybrid Retrieval

    Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology (BUET)

  14. CCCE: A Continuous Code Calibration Engine for Autonomous Enterprise Codebase Maintenance via Knowledge Graph Traversal and Adaptive Decision Gating

    Apr 10, 2026Santhosh Kusuma Kumar ParimiSoftware EngineeringAutomated Software Engineering

    Independent Researcher Austin, TX, USA

  15. Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision

    Apr 8, 2026Hong Yi Lin, Chunhua Liu, Haoyu Gao +2Confidence Estimation in Language ModelsLanguage Model Calibration

  16. QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization

    Apr 7, 2026Changxin Ke, Rui Zhang, Jiaming Guo +10Automated Program RepairLLM Code Generation

    State Key Lab of Processors, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences · Institute of Microelectronics, CAS

  17. On the Role of Fault Localization Context for LLM-Based Program Repair

    Apr 7, 2026Melika Sepidband, Hung Viet Pham, Hadi HemmatiFault LocalizationAutomated Program Repair

    York University, Toronto, Canada

  18. Improving MPI Error Detection and Repair with Large Language Models and Bug References

    Apr 2, 2026Scott Piersall, Yang Gao, Shenyang Liu +1Language Model Error DetectionAutomated Program Repair

    Dept. of Computer Science, University of Central Florida, Orlando, 32816, FL, US

  19. From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

    Apr 2, 2026Nikolai Ludwig, Wasi Uddin Ahmad, Somshubra Majumdar +1Software Engineering AgentsLLM Agent Training

    NVIDIA Santa Clara, CA 95051, USA

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

    Mar 31, 2026Joseph Townsend, Chandresh Pravin, Kwun Ho Ngan +1Repository-Level Program RepairAutomated Program Repair

    Fujitsu Research of Europe, UK

  21. Designing FSMs Specifications from Requirements with GPT 4.0

    Mar 31, 2026Omer Nguena Timo, Paul-Alexis Rodriguez, Florent AvellanedaFinite-State MachineModel-Based Systems Engineering

    Universit´e du Qu´ebec en Outaouais, Quebec-Canada · Universit´e Paris-Saclay, Paris-France · Universit´e du Qu´ebec `a Montr´eal, Qu´ebec-Canada

  22. ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair

    Mar 28, 2026Jia Li, Zeyang Zhuang, Zhuangbin Chen +3Automated Program RepairSoftware Engineering Benchmarks

    The Chinese University of Hong Kong, Hong Kong, China · School of Software Engineering, Sun Yat-sen University, Zhuhai, China · Sun Yat-sen University, Guangzhou, China

  23. Agentic Harness for Real-World Compilers

    Mar 20, 2026Yingwei Zheng, Cong Li, Shaohua Li +2LLM Agent HarnessesAutomated Program Repair

    Southern University of Science and Technology · ETH Zurich · The Chinese University of Hong Kong

  24. Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2

    Mar 20, 2026Yu-Ning Qiu, Lin-Feng Zou, Jiong-Da Wang +2ARC-AGINeuro-Symbolic Reasoning

    Nanjing University, Nanjing, China

  25. FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair

    Mar 18, 2026Ruize Ma, Yilei Jiang, Shilin Zhang +7Automated Program RepairMultimodal Agents

    Nanjing University · SenseTime · The Chinese University of Hong Kong +1

  26. VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?

    Mar 16, 2026Srijan Bansal, Jiao Fangkai, Yilun Zhou +3LLM Self-CorrectionLanguage Model Error Detection

    Salesforce AI Research · Nanyang Technological University · A*STAR

  27. PCodeTrans: Translate Decompiled Pseudocode to Compilable and Executable Equivalent

    Mar 16, 2026Yuxin Cui, Zeyu Gao, Shuxian He +2Code TranslationSoftware Reverse Engineering

    Tsinghua University · Wuhan University · Institute of Information Engineering, CAS

  28. Why LLMs Fail: A Failure Analysis and Partial Success Measurement for Automated Security Patch Generation

    Mar 10, 2026Amir Al-MaamariAutomated Program RepairSoftware Security

    University of Passau, Germany

  29. SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training

    Mar 9, 2026Xin-Cheng Wen, Binbin Chen, Haoxuan Lan +3Software Engineering AgentsLLM Agent Training

    Ant Group · The Chinese University of Hong Kong

  30. ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense

    Mar 2, 2026Nancy Lau, Louis Sloot, Jyoutir Raj +6AI Agent Security BenchmarksLLMs for Cybersecurity

    UC Santa Cruz · Carnegie Mellon University · Independent +2