AwesomeLLM4APR

<h1 align = "center">🤖 Awesome LLM for APR</h1> <p align="center"> <a href="https://awesome.re"><img src="https://awesome.re/badge.svg"></a> <a href="https://arxiv.org/abs/2405.01466"><img src="https://img.shields.io/badge/arXiv-2405.01466-blue.svg"></a> <img src="https://img.shields.io/github/stars/iSEngLab/AwesomeLLM4APR?color=yellow&label=Stars"> <img src="https://img.shields.io/badge/PRs-Welcome-red"> <img src="https://img.shields.io/github/last-commit/iSEngLab/AwesomeLLM4APR"> </p>

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 [