🤖 Awesome LLM for APR

We use an LLM-based bot to automatically fetch and summarize new LLM4APR papers, with regular human curation to ensure quality. You can check the raw bot updates in this separate update_file, or explore the curated summaries on our summary site.

📖 Contents

• 👏 Citation
• 💡 Repair Scenarios
  • Semantic Bug
  • Security Vulnerability
  • Syntax Error
  • Programming Problem
  • Static Warning
  • Self-Debug
  • Type Error
  • Web UI Test
  • Repository-level Issue
  • Smart Contract
  • Hardware Bug
  • Performance Bug
  • API Misuse
  • Formal Specification
  • Crash Bug
  • Test Case
  • Error-handling Bug
  • Formal Proof
  • Translation Bug
  • GitHub Issue
  • Code Review
  • Motion Planner
• 🙆 Human Study
• 🙅 Patch Correctness Assessment
• 📊 Benchmark
• 🤔 Related APR Surveys

👏 Citation

@article{zhang2024survey,
  title={A Systematic Literature Review on Large Language Models for Automated Program Repair},
  author={Zhang, Quanjun and Fang, Chunrong and Xie, Yang and Ma, Yuxiang and Sun, Weisong and Yang, Yun and Chen, Zhenyu},
  journal={arXiv preprint arXiv:2405.01466}
  year={2024}
}

🔥🔥 New Papers

1. Divide-and-Conquer: Automating Code Revisions via Localization-and-Revision [2024-TOSEM] [repo]
2. Error Delayed Is Not Error Handled: Understanding and Fixing Propagated Error-Handling Bugs [2025-FSE/ESEC] [repo]
3. An Empirical Evaluation of Pre-trained Large Language Models for Repairing Declarative Formal Specifications [2024-EMSE] [repo]
4. Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing [2025-ASE] [repo]
5. SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains? [2025-ICLR] [repo]
6. DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models [2025-ICSE] [repo]
7. Combining Logic and Large Language Models for Assisted Debugging and Repair of ASP Programs [2025-ICST] [repo]
8. Less is More: Adaptive Program Repair with Bug Localization and Preference Learning [2025-AAAI] [repo]
9. Exploring Parameter-Efficient Fine-Tuning of Large Language Model on Automated Program Repair [2024-ASE] [repo]
10. FastFixer: An Efficient and Effective Approach for Repairing Programming Assignments [2024-ASE] [repo]
11. Investigating Large Language Models Capabilities for Automatic Code Repair in Python [2024-Cluster Computing] [repo]
12. Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization [2025-AAAI] [repo]
13. Code repair with llms gives an exploration-exploitation tradeoff [2024-NeurIPS] [repo]
14. Automated Program Repair for Introductory Programming Assignments [2024-TLT]
15. Investigating the Transferability of Code Repair for Low-Resource Programming Languages [2025-NAACL] [repo]
16. CREF: An LLM-based Conversational Software Repair Framework for Programming Tutors [2024-ISSTA] [repo]
17. RePair: Automated Program Repair with Process-based Feedback [2024-ACL] [repo]
18. MASAI: Modular Architecture for Software-engineering AI Agents [2024-NeurIPS]
19. CodeR: Issue Resolving with Multi-Agent and Task Graphs [2024-arxiv] [repo]
20. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering [2024-NeurIPS] [repo]
21. AutoCodeRover: Autonomous Program Improvement [2024-ISSTA] [repo]
22. MarsCode Agent: AI-native Automated Bug Fixing [2024-arxiv]
23. Enhancing Automated Program Repair with Solution Design [2024-ASE] [repo]
24. Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolution [2025-MSR] [repo]
25. OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution [2025-ISSTA] [repo]
26. SWE-GPT: A Process-Centric Language Model for Automated Software Improvement [2025-ISSTA] [repo]
27. SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents [2025-NeurIPS] [repo]
28. SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement [2025-ICLR] [repo]
29. RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph [2025-ICLR] [repo]
30. SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution [2025-NeurIPS] [repo]
31. Demystifying LLM-based Software Engineering Agents [2025-FSE/ESEC] [repo]
32. MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution [2025-NeurIPS]
33. OpenHands: An Open Platform for AI Software Developers as Generalist Agents [2025-ICLR] [repo]
34. Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration [2025-FSE-Companion] [repo]
35. A Case Study of LLM for Automated Vulnerability Repair: Assessing Impact of Reasoning and Patch Validation Feedback [2024-AIware] [repo]
36. VulAdvisor: Natural Language Suggestion Generation for Software Vulnerability Repair [2024-ASE] [repo]
37. Teaching AI the ‘Why’ and ‘How’ of Software Vulnerability Fixes [2025-FSE/ESEC] [repo]
38. APPATCH: Automated Adaptive Prompting Large Language Models for Real-World Software Vulnerability Patching [2025-USENIX Security] [repo]
39. Closing the Gap: A User Study on the Real-world Usefulness of AI-powered Vulnerability Detection & Repair in the IDESecurityArtifact-FunctionalArtifact-AvailableArtifact-Reusable [2025-ICSE] [repo]
40. PATCHAGENT: A Practical Program Repair Agent Mimicking Human Expertise [2025-USENIX Security] [repo]
41. CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair [2024-ICLR]
42. From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging [2024-arxiv] [repo]
43. When Large Language Models Confront Repository-Level Automatic Program Repair: How Well They Done? [2024-ICSE]
44. T5APR: Empowering Automated Program Repair across Languages through Checkpoint Ensemble [2024-JSS] [repo]
45. A Deep Dive into Large Language Models for Automated Bug Localization and Repair [2024-FSE/ESEC]
46. Benchmarking Automated Program Repair: An Extensive Study on Both Real-World and Artificial Bugs [2024-ISSTA]
47. Automated Program Repair via Conversation: Fixing 162 out of 337 bugs for $0.42 each using chatgpt [2024-ISSTA]
48. How Far Can We Go with Practical Function-Level Program Repair? [2024-arxiv] [repo]
49. Exploring and Lifting the Robustness of LLM-powered Automated Program Repair with Metamorphic Testing [2024-arxiv]
50. Thinkrepair: Self-directed automated program repair [2024-ISSTA] [repo]
51. Hierarchical Knowledge Injection for Improving LLM-based Program Repair [2025-ASE] [repo]
52. Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repair [2025-TOSEM] [repo]
53. APRMCTS: Improving LLM-based Automated Program Repair with Iterative Tree Search [2025-ASE] [repo]
54. Demystifying Memorization in LLM-based Program Repair via a General Hypothesis Testing Framework [2025-FSE/ESEC] [repo]
55. Hybrid Automated Program Repair by Combining Large Language Models and Program Analy [2025-TOSEM] [repo]
56. When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair [2025-TOSEM] [repo]
57. The Impact of Fine-tuning Large Language Models on Automated Program Repair [2025-ICSME] [repo]
58. Knowledge-Enhanced Program Repair for Data Science Code [2025-ICSE] [repo]
59. The Fact Selection Problem in LLM-Based Program Repair [2025-ICSE] [repo]
60. The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models [2025-EASE] [repo]
61. MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning [2025-TOSEM]
62. Adversarial Reasoning for Repair Based on Inferred Program Intent [2025-ISSTA] [repo]
63. Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair viaRepair Ingredients Search [2025-ICSE] [repo]
64. Aligning the Objective of LLM-based Program Repair [2025-ICSE] [repo]
65. One Size Does Not Fit All: Multi-granularity Patch Generation for Better Automated Program Repair [2024-ISSTA] [repo]
66. Template-Guided Program Repair in the Era of Large Language Models [2025-ICSE] [repo]
67. Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models [2024-arxiv] [repo]
68. HapRepair: Learn to Repair OpenHarmony Apps [2025-FSE/ESEC] [repo]
69. CORE: Resolving Code Quality Issues using LLMs [2024-FSE/ESEC]
70. FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair [2024-TSE] [repo]
71. NIODebugger: A Novel Approach to Repair Non-Idempotent-Outcome Tests with LLM-Based Agent [2025-ICSE] [repo]
72. RetypeR: Integrated Retrieval-based Automatic Program Repair for Python Type Errors [2024-ICSME] [repo]

💡 Repair Scenarios

Semantic Bug

1. From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging [2024-arxiv] [repo]
2. When Large Language Models Confront Repository-Level Automatic Program Repair: How Well They Done? [2024-ICSE]
3. T5APR: Empowering Automated Program Repair across Languages through Checkpoint Ensemble [2024-JSS] [repo]
4. A Deep Dive into Large Language Models for Automated Bug Localization and Repair [2024-FSE/ESEC]
5. Benchmarking Automated Program Repair: An Extensive Study on Both Real-World and Artificial Bugs [2024-ISSTA] [repo]
6. Automated Program Repair via Conversation: Fixing 162 out of 337 bugs for $0.42 each using chatgpt [2024-ISSTA] [repo]
7. How Far Can We Go with Practical Function-Level Program Repair? [2024-arxiv] [repo]
8. Exploring and Lifting the Robustness of LLM-powered Automated Program Repair with Metamorphic Testing [2024-arxiv]
9. Thinkrepair: Self-directed automated program repair [2024-ISSTA] [repo]
10. Hierarchical Knowledge Injection for Improving LLM-based Program Repair [2025-ASE] [repo]
11. Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repair [2025-TOSEM] [repo]
12. APRMCTS: Improving LLM-based Automated Program Repair with Iterative Tree Search [2025-ASE] [repo]
13. Demystifying Memorization in LLM-based Program Repair via a General Hypothesis Testing Framework [2025-FSE/ESEC] [repo]
14. Hybrid Automated Program Repair by Combining Large Language Models and Program Analy [2025-TOSEM] [repo]
15. When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair [2025-TOSEM] [repo]
16. The Impact of Fine-tuning Large Language Models on Automated Program Repair [2025-ICSME] [repo]
17. Knowledge-Enhanced Program Repair for Data Science Code [2025-ICSE] [repo]
18. The Fact Selection Problem in LLM-Based Program Repair [2025-ICSE] [repo]
19. The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models [2025-EASE] [repo]
20. MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning [2025-TOSEM]
21. Adversarial Reasoning for Repair Based on Inferred Program Intent [2025-ISSTA] [repo]
22. Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair viaRepair Ingredients Search [2025-ICSE] [repo]
23. Aligning the Objective of LLM-based Program Repair [2025-ICSE] [repo]
24. One Size Does Not Fit All: Multi-granularity Patch Generation for Better Automated Program Repair [2024-ISSTA] [repo]
25. Template-Guided Program Repair in the Era of Large Language Models [2025-ICSE] [repo]
26. Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models [2024-arxiv] [repo]
27. HapRepair: Learn to Repair OpenHarmony Apps [2025-FSE/ESEC] [repo]
28. Automated program repair for variability bugs in software product line systems[2024-JSS] [paper]
29. A Unified Debugging Approach via LLM-Based Multi-Agent Synergy [2024-arxiv] [paper] [repo]
30. How Far Can We Go with Practical Function-Level Program Repair? [2024-arxiv] [paper] [repo]
31. Automated program repair via conversation: Fixing 162 out of 337 bugs for $0.42 each using chatgpt[2024-ISSTA] [paper]
    Old Version: Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT [2023-arxiv] [paper]
32. A Novel Approach for Automatic Program Repair using Round-Trip Translation with Large Language Models [2024-arxiv] [paper] [repo]
33. Out of Context: How important is Local Context in Neural Program Repair? [2024-ICSE] [paper] [repo]
34. Multi-Objective Fine-Tuning for Enhanced Program Repair with LLMs [2024-arxiv] [paper]
35. Aligning the Objective of LLM-based Program Repair [2025-ICSE] [paper] [repo]
36. ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs [2024-arxiv] [paper]
37. Exploring the Potential of Pre-Trained Language Models of Code for Automated Program Repair [2024-Electronics] [paper]
38. CigaR: Cost-efficient Program Repair with LLMs [2024-arxiv] [paper] [repo]
39. The Fact Selection Problem in LLM-Based Program Repair [2024-arxiv] [paper] [repo]
40. A Novel Approach for Automated Program Repair using Round-Trip Translation with Large Language Models [2024-arxiv] [paper] [repo]
41. RepairAgent: An Autonomous, LLM-Based Agent for Program Repair [2024-arxiv] [paper]
42. A Deep Dive into Large Language Models for Automated Bug Localization and Repair [2024-FSE/ESEC] [paper]
43. Automated Program Repair in the Era of Large Pre-trained Language Models [2023-ICSE] [paper] [repo]
44. Repair Is Nearly Generation: Multilingual Program Repair with LLMs [2023-AAAI] [paper]
45. Retrieval-based prompt selection for code-related few-shot learning [2023-ICSE] [paper] [repo]
46. What makes good in-context demonstrations for code intelligence tasks with llms? [2023-ASE] [paper] [repo]
47. Fully Autonomous Programming with Large Language Models [2023-GECCO] [paper] [repo]
48. Automated Program Repair Using Generative Models for Code Infilling [2023-AIED] [paper] [repo]
49. STEAM: Simulating the InTeractive BEhavior of ProgrAMmers for Automatic Bug Fixing [2023-arxiv] [paper]
50. Conversational automated program repair [2023-arxiv] [paper]
51. Is ChatGPT the Ultimate Programming Assistant--How far is it? [2023-arxiv] [paper] [repo]
52. Using Large Language Models for Bug Localization and Fixing [2023-iCAST] [paper]
53. An Empirical Study on Fine-Tuning Large Language Models of Code for Automated Program Repair [2023-ASE] [paper] [repo]
54. An Evaluation of the Effectiveness of OpenAI's ChatGPT for Automated Python Program Bug Fixing using QuixBugs [2023-iSEMANTIC] [paper]
55. Explainable Automated Debugging via Large Language Model-driven Scientific Debugging [2023-arxiv] [paper]
56. The Right Prompts for the Job: Repair Code-Review Defects with Large Language Model [2023-arxiv] [paper]
57. Impact of Code Language Models on Automated Program Repair [2023-ICSE] [paper] [repo]
58. Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions [2023-arxiv] [paper]
59. The Plastic Surgery Hypothesis in the Era of Large Language Models [2023-ASE] [paper] [repo]
60. Exploring the Limits of ChatGPT in Software Security Applications [2023-arxiv] [paper]
61. CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation [2023-arxiv] [paper] [repo]
62. Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering [2023-arxiv] [paper] [repo]
63. Training Language Models for Programming Feedback Using Automated Repair Tools [2023-AIED] [paper] [repo]
64. RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair [2023-arxiv] [paper] [repo]
65. Automated Code Editing with Search-Generate-Modify [2023-arxiv] [paper] [repo]
66. RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair [2023-FSE/ESEC] [paper] [repo]
67. Neural Program Repair with Program Dependence Analysis and Effective Filter Mechanism [2023-arxiv] [paper]
68. Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback [2023-arxiv] [paper] [repo]
69. A study on Prompt Design, Advantages and Limitations of ChatGPT for Deep Learning Program Repair [2023-arxiv] [paper]
70. Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair [2023-FSE/ESEC] [paper] [repo]
71. Gamma: Revisiting Template-Based Automated Program Repair Via Mask Prediction [2023-ASE] [paper] [repo]
72. An Extensive Study on Model Architecture and Program Representation in the Domain of Learning-based Automated Program Repair [2023-APR] [paper] [repo]
73. Improving Automated Program Repair with Domain Adaptation [2023-TOSEM] [paper] [repo]
74. Enhancing Code Language Models for Program Repair by Curricular Fine-tuning Framework [2023-ICSME] [paper]
75. The potential use of ChatGPT for debugging and bug fixing [2023-] [paper]
76. CIRCLE: Continual Repair across Programming Languages [2022-ISSTA] [paper] [repo]
77. Towards JavaScript program repair with Generative Pre-trained Transformer (GPT-2) [2022-APR] [paper] [repo]
78. Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar [2022-ICLR] [paper]
79. Patch Generation with Language Models: Feasibility and Scaling Behavior [2022-ICLR] [paper]
80. Can OpenAI's codex fix bugs?: an evaluation on QuixBugs [2022-APR] [paper]
81. An Analysis of the Automatic Bug Fixing Performance of ChatGPT [2022-APR] [paper] [repo]
82. Less training, more repairing please: revisiting automated program repair via zero-shot learning [2022-FSE/ESEC] [paer] [repo]
83. Framing Program Repair as Code Completion [2022-APR] [paper] [repo]
84. DEAR A Novel Deep Learning-based Approach for Automated Program Repair [2022-ICSE] [paper] [repo]
85. Generating Bug-Fixes Using Pretrained Transformers [2021-PLDI] [paper]
86. Applying CodeBERT for Automated Program Repair of Java Simple Bugs [2021-MSR] [paper] [repo]
87. CURE Code-Aware Neural Machine Translation for Automatic Program Repair [2021-ICSE] [paper] [repo]
88. How to Understand Whole Software Repository? [2024-arXiv] [paper]

Security Vulnerability

1. One Size Does Not Fit All: Multi-granularity Patch Generation for Better Automated Program Repair [2024-ISSTA] [repo]
2. Template-Guided Program Repair in the Era of Large Language Models [2025-ICSE] [repo]
3. A Case Study of LLM for Automated Vulnerability Repair: Assessing Impact of Reasoning and Patch Validation Feedback [2024-AIware] [repo]
4. VulAdvisor: Natural Language Suggestion Generation for Software Vulnerability Repair [2024-ASE] [repo]
5. Teaching AI the ‘Why’ and ‘How’ of Software Vulnerability Fixes [2025-FSE/ESEC] [repo]
6. APPATCH: Automated Adaptive Prompting Large Language Models for Real-World Software Vulnerability Patching [2025-USENIX Security] [repo]
7. Closing the Gap: A User Study on the Real-world Usefulness of AI-powered Vulnerability Detection & Repair in the IDESecurityArtifact-FunctionalArtifact-AvailableArtifact
8. Reusable [2025-ICSE] [repo]
9. PATCHAGENT: A Practical Program Repair Agent Mimicking Human Expertise [2025-USENIX Security] [repo]
10. 🔥Automated Repair of AI Code with Large Language Models and Formal Verification [2024-arXiv] [paper]
11. 🔥NAVRepair: Node-type Aware C/C++ Code Vulnerability Repair [2024-arxiv] [paper]
12. Enhanced Automated Code Vulnerability Repair using Large Language Models [2024-arxiv] [paper]
13. Out of Sight, Out of Mind: Better Automatic Vulnerability Repair by Broadening Input Ranges and Sources [2024-ICSE] [paper] [repo]
14. A Study of Vulnerability Repair in JavaScript Programs with Large Language Models [2024-arxiv] [paper] [repo]
15. Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities [2024-arxiv] [paper]
16. Pre-trained Model-based Automated Software Vulnerability Repair: How Far are We? [2023-TDSC] [paper] [repo]
17. Examining zero-shot vulnerability repair with large language models [2023-S&P] [paper] [repo]
18. An Empirical Study on Fine-Tuning Large Language Models of Code for Automated Program Repair [2023-ASE] [paper] [repo]
19. A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification [2023-arxiv] [paper]
20. Exploring the Limits of ChatGPT in Software Security Applications [2023-arxiv] [paper]
21. ZeroLeak: Using LLMs for Scalable and Cost Effective Side-Channel Patching [2023-arxiv] [paper]
22. How ChatGPT is Solving Vulnerability Management Problem [2023-arxiv] [paper] [repo]
23. How Effective Are Neural Networks for Fixing Security Vulnerabilities [2023-ISSTA] [paper] [repo]
24. Vision Transformer-Inspired Automated Vulnerability Repair [2023-TOSEM] [paper] [repo]
25. Can large language models find and fix vulnerable software? [2023-arxiv] [paper]
26. VulRepair: A T5-Based Automated Software Vulnerability Repair [2022-FSE/ESEC] [paper] [repo]

Syntax Error

1. HapRepair: Learn to Repair OpenHarmony Apps [2025-FSE/ESEC] [repo]
2. A Novel Approach for Automated Program Repair using Round-Trip Translation with Large Language Models [2024-arxiv] [paper] [repo]
3. Repair Is Nearly Generation: Multilingual Program Repair with LLMs [2023-AAAI] [paper]
4. Fixing Rust Compilation Errors using LLMs [2023-arxiv] [paper]
5. An Empirical Study on Fine-Tuning Large Language Models of Code for Automated Program Repair [2023-ASE] [paper] [repo]
6. A Chain of AI-based Solutions for Resolving FQNs and Fixing Syntax Errors in Partial Code [2023-arxiv] [paper] [repo]
7. The Right Prompts for the Job: Repair Code-Review Defects with Large Language Model [2023-arxiv] [paper]
8. SYNSHINE: improved fixing of Syntax Errors [2022-TSE] [paper] [repo]

Programming Problem

1. 🔥Combining Logic and Large Language Models for Assisted Debugging and Repair of ASP Programs [2025-ICST] [repo]
2. 🔥Less is More: Adaptive Program Repair with Bug Localization and Preference Learning [2025-AAAI] [repo]
3. 🔥Exploring Parameter-Efficient Fine-Tuning of Large Language Model on Automated Program Repair [2024-ASE] [repo]
4. 🔥FastFixer: An Efficient and Effective Approach for Repairing Programming Assignments [2024-ASE] [repo]
5. 🔥Investigating Large Language Models Capabilities for Automatic Code Repair in Python [2024-Cluster Computing] [repo]
6. 🔥Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization [2025-AAAI] [repo]
7. 🔥Code repair with llms gives an exploration-exploitation tradeoff [2024-NeurIPS] [repo]
8. 🔥Automated Program Repair for Introductory Programming Assignments [2024-TLT] [repo]
9. 🔥Investigating the Transferability of Code Repair for Low-Resource Programming Languages [2025-NAACL] [repo]
10. 🔥CREF: An LLM-based Conversational Software Repair Framework for Programming Tutors [2024-ISSTA] [repo]
11. 🔥RePair: Automated Program Repair with Process-based Feedback [2024-ACL] [repo]
12. CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair [2024-arXiv-NVIDIA] [paper]
13. A Unified Debugging Approach via LLM-Based Multi-Agent Synergy [2024-arXiv] [paper] [repo]
14. PyDex: Repairing Bugs in Introductory Python Assignments using LLMs [2024-OOPSLA] [paper] [repo]
15. DebugBench: Evaluating Debugging Capability of Large Language Models [2024-arxiv] [paper] [repo]
16. ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs [2024-arxiv] [paper]
17. ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair [2024-arxiv] [paper] [repo]
18. Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments [2024-arxiv] [paper]
19. Improved Program Repair Methods using Refactoring with GPT Models [2024-SIGCSE TS] [paper] [repo]
20. A critical review of large language model on software engineering: An example from chatgpt and automated program repair [2023-arxiv] [paper] [repo]
21. Automated Repair of Programs from Large Language Models [2023-ICSE] [paper] [repo]
22. FixEval: Execution-based Evaluation of Program Fixes for Programming Problems [2023-APR] [paper] [repo]
23. Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues [2023-TOSEM] [paper] [repo]
24. Repairing bugs in python assignments using large language models [2022-arixv] [paper]

Static Warning

1. CORE: Resolving Code Quality Issues using LLMs [2024-FSE/ESEC]
2. Frustrated with Code Quality Issues? LLMs can Help! [2024-FSE/ESEC] [paper] [repo]
3. SkipAnalyzer: An Embodied Agent for Code Analysis with Large Language Models [2023-arxiv] [paper] [repo]
4. RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair [2023-FSE/ESEC] [paper] [repo]
5. InferFix: End-to-End Program Repair with LLMs over Retrieval-Augmented Prompts [2023-FSE/ESEC] [paper] [repo]
6. Can LLMs Patch Security Issues [2023-arxiv] [paper] [repo]
7. Improving Automated Program Repair with Domain Adaptation [2023-TOSEM] [paper] [repo]
8. An empirical study of deep transfer learning-based program repair for Kotlin projects [2022-FSE/ESEC] [paper]
9. TFix-Learning to Fix Coding Errors with a Text-to-Text Transformer [2021-PMLR] [paper] [repo]

Self-Debug

1. Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models [2024-arxiv] [repo]
2. CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair [2024-ICLR]
3. From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging [2024-arXiv] [paper] [repo]
4. Teaching Large Language Models to Self-Debug [2024-ICLR] [paper]
5. OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement [2024-arxiv] [paper] [repo]
6. CYCLE: Learning to Self-Refine the Code Generation [2024-OOPSLA] [paper] [repo]
7. LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step [2024-arxiv] [paper] [repo]
8. Leveraging Print Debugging to Improve Code Generation in Large Language Models [2024-arxiv] [paper]
9. SelfEvolve: A Code Evolution Framework via Large Language Models [2023-arxiv] [paper]
10. Self-Refine: Iterative Refinement with Self-Feedback [2023-NeurIPS] [paper] [repo]
11. AgentCoder: Multi Agent-Code Generation with Iterative Testing and Optimisation [2023-arxiv] [paper]
12. Self-Edit: Fault-Aware Code Editor for Code Generation [2023-ACL] [paper] [repo]
13. Is Self-Repair a Silver Bullet for Code Generation? [2023-ICLR] [paper] [repo]

Type Error

1. RetypeR: Integrated Retrieval-based Automatic Program Repair for Python Type Errors [2024-ICSME] [repo]
2. Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Errors [2024-ICSE] [paper] [repo]
3. PyTy: Repairing Static Type Errors in Python [2024-ICSE] [paper] [repo]
4. GPT-3-Powered Type Error Debugging: Investigating the Use of Large Language Models for Code Repair [2023-SLE] [paper] [repo]

Web UI Test

1. Guiding ChatGPT to Fix Web UI Tests via Explanation-Consistency Checking [2023-arxiv] [paper]

Repository-level Issue

1. MASAI: Modular Architecture for Software-engineering AI Agents [2024-NeurIPS]
2. CodeR: Issue Resolving with Multi-Agent and Task Graphs [2024-arxiv] [repo]
3. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering [2024-NeurIPS] [repo]
4. AutoCodeRover: Autonomous Program Improvement [2024-ISSTA] [repo]
5. MarsCode Agent: AI-native Automated Bug Fixing [2024-arxiv]
6. Enhancing Automated Program Repair with Solution Design [2024-ASE] [repo]
7. Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolution [2025-MSR] [repo]
8. OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution [2025-ISSTA] [repo]
9. SWE-GPT: A Process-Centric Language Model for Automated Software Improvement [2025-ISSTA] [repo]
10. SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents [2025-NeurIPS] [repo]
11. SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement [2025-ICLR] [repo]
12. RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph [2025-ICLR] [repo]
13. SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution [2025-NeurIPS] [repo]
14. Demystifying LLM-based Software Engineering Agents [2025-FSE/ESEC] [repo]
15. MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution [2025-NeurIPS] [repo]
16. OpenHands: An Open Platform for AI Software Developers as Generalist Agents [2025-ICLR] [repo]
17. Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration [2025-FSE-Companion] [repo]

Smart Contract

1. ACFIX: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contracts [2024-arxiv] [paper]
2. Evaluating ChatGPT for Smart Contracts Vulnerability Correction [2023-COMPSAC] [paper] [repo]

Hardware Bug

1. CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair [2024-ICLR]
2. On Hardware Security Bug Code Fixes By Prompting Large Language Models [2024-TIFS] [paper] [repo]
   Its pre-print: Fixing Hardware Security Bugs with Large Language Models [2022-arXiv] [paper]
3. HDLdebugger: Streamlining HDL debugging with Large Language Models [2024-arxiv] [paper]
4. RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Models [2023-arxiv] [paper]
5. LLM4SecHW: Leveraging domain-specific large language model for hardware debugging [2023-AsianHOST] [paper]

GUI Bug

1. Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing [2025-ASE] [repo]
2. SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains? [2025-ICLR] [repo]
3. DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models [2025-ICSE] [repo]

Performance Bug

1. RAPGen: An Approach for Fixing Code Inefficiencies in Zero-Shot [2023-arxiv] [paper]
2. DeepDev-PERF: A Deep Learning-Based Approach for Improving Software Performance [2022-FSE/ESEC] [paper] [repo]

API Misuse

1. Evaluating Pre-trained Language Models for Repairing API Misuses [2023-arxiv] [paper] [repo]

Formal Specification

1. An Empirical Evaluation of Pre-trained Large Language Models for Repairing Declarative Formal Specifications [2024-EMSE] [repo]

Crash Bug

1. Resolving Crash Bugs via Large Language Models: An Empirical Study [2023-arxiv] [paper] [repo]

Test Case

1. FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair [2024-TSE] [repo]
2. NIODebugger: A Novel Approach to Repair Non-Idempotent-Outcome Tests with LLM-Based Agent [2025-ICSE] [repo]
3. Automated Test Case Repair Using Language Models [2024-arxiv] [paper]
4. Identify and Update Test Cases when Production Code Changes: A Transformer-based Approach [2023-ASE]

Error-handling Bug

1. Error Delayed Is Not Error Handled: Understanding and Fixing Propagated Error-Handling Bugs [2025-FSE/ESEC] [repo]

Formal Proof

1. Baldur: Whole-Proof Generation and Repair with Large Language Models [2023-FSE/ESEC] [paper]

Translation Bug

1. Lost in Translation: A Study of Bugs Introduced by Large Language Models while Translating Code [2024-ICSE] [paper] [repo]

GitHub Issue

1. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? [2024-ICLR] [paper] [repo]

Code Review

1. Divide-and-Conquer: Automating Code Revisions via Localization-and-Revision [2024-TOSEM] [repo]
2. Exploring the Potential of ChatGPT in Automated Code Refinement: An Empirical Study [2024-ICSE] [paper] [repo]

Motion Planner

1. DrPlanner: Diagnosis and Repair of Motion Planners Using Large Language Models [2024-arxiv] [paper] [repo]

🙆 Human Study

1. Exploring Experiences with Automated Program Repair in Practice [2024-ICSE] [paper]
2. Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models [2024-arxiv] [paper] [repo]
3. An Empirical Study of Adoption of ChatGPT for Bug Fixing among Professional Developers [2023-ITA] [paper]

🙅 Patch Correctness Assessment

1. 🔥Leveraging Large Language Model for Automatic Patch Correctness Assessment[2024-TSE] [paper]
2. APPT Boosting Automated Patch Correctness Prediction via Pre-trained Language Model [2024-TSE] [paper] [repo]
3. The Best of Both Worlds: Combining Learned Embeddings with Engineered Features for Accurate Prediction of Correct Patches [2023-TOSME] [paper] [repo]
4. Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning [2023-TSE] [paper] [repo]
5. PatchZero: Zero-Shot Automatic Patch Correctness Assessment [2023-arxiv] [paper]
6. Is this Change the Answer to that Problem? Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctness [2021-ASE] [paper] [repo]
7. Evaluating representation learning of code changes for predicting patch correctness in program repair [2020-ASE] [paper] [repo]

📊 Benchmark

1. 🔥Exploring Parameter-Efficient Fine-Tuning of Large Language Model on Automated Program Repair[2024-ASE] [paper]
2. 🔥MuBench: Benchmarking Automated Program Repair: An Extensive Study on Both Real-World and Artificial Bugs [2024-ISSTA] [paper]
3. CodeEditorBench: Evaluating Code Editing Capability of Large Language Models [2024-arxiv] [paper] [repo]
4. GitBug-Java: A Reproducible Benchmark of Recent Java Bugs [2024-arxiv] [paper] [repo]
5. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? [2024-ICLR] [paper] [repo]
6. DebugBench: Evaluating Debugging Capability of Large Language Models [2024-arxiv] [paper] [repo]
7. ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair [2024-arxiv] [paper] [repo]
8. A critical review of large language model on software engineering: An example from chatgpt and automated program repair [2023-arxiv] [paper] [repo]
9. CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation [2023-arxiv] [paper] [repo]
10. FixEval: Execution-based Evaluation of Program Fixes for Programming Problems [2023-APR] [paper] [repo]

🤔 Related APR Surveys

1. A Survey of Learning-based Automated Program Repair [2023-TOSEM] [paper] [repo]
2. Automatic Software Repair: A Bibliography [2018-CSUR] paper]
3. Automatic Software Repair: A Survey [2017-TSE] paper]

Star History