{"id":77807,"url":"https://github.com/iSEngLab/AwesomeLLM4APR","name":"AwesomeLLM4APR","description":"[TOSEM 2026]A Systematic Literature Review on Large Language Models for Automated Program Repair","projects_count":287,"last_synced_at":"2026-09-25T14:00:27.730Z","repository":{"id":236507590,"uuid":"775841170","full_name":"iSEngLab/AwesomeLLM4APR","owner":"iSEngLab","description":"[TOSEM 2026]A Systematic Literature Review on Large Language Models for Automated Program Repair","archived":false,"fork":false,"pushed_at":"2026-05-01T06:33:18.000Z","size":559,"stargazers_count":246,"open_issues_count":0,"forks_count":20,"subscribers_count":9,"default_branch":"main","last_synced_at":"2026-09-05T17:26:07.365Z","etag":null,"topics":["awesome","large-language-models","program-repair","software-engineering"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2405.01466","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/iSEngLab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-03-22T06:34:42.000Z","updated_at":"2026-08-20T05:15:36.000Z","dependencies_parsed_at":"2024-04-27T14:25:52.968Z","dependency_job_id":"8a149d91-cf58-47fa-8e59-d49c359c3241","html_url":"https://github.com/iSEngLab/AwesomeLLM4APR","commit_stats":null,"previous_names":["isenglab/awesomellm4apr"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/iSEngLab/AwesomeLLM4APR","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iSEngLab%2FAwesomeLLM4APR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iSEngLab%2FAwesomeLLM4APR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iSEngLab%2FAwesomeLLM4APR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iSEngLab%2FAwesomeLLM4APR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iSEngLab","download_url":"https://codeload.github.com/iSEngLab/AwesomeLLM4APR/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iSEngLab%2FAwesomeLLM4APR/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":341189360,"owners_count":37679287,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-22T15:14:58.755Z","status":"online","status_checked_at":"2026-09-25T02:00:20.896Z","response_time":55,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2024-11-13T00:00:27.833Z","updated_at":"2026-09-25T14:00:27.730Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["🤔 Related APR Surveys","💡 Repair Scenarios","📊 Benchmark","🔥🔥 New Papers","🙆 Human Study","🙅 Patch Correctness Assessment","Star History"],"sub_categories":["Motion Planner","Self-Debug","Security Vulnerability","Semantic Bug","Syntax Error","Programming Problem","Static Warning","Type Error","Web UI Test","Smart Contract","Hardware Bug","Performance Bug","API Misuse","Crash Bug","Test Case","Formal Proof","Code Review","Translation Bug"],"readme":"\u003ch1 align = \"center\"\u003e🤖 Awesome LLM for APR\u003c/h1\u003e\r\n\u003cp align=\"center\"\u003e\r\n  \u003ca href=\"https://awesome.re\"\u003e\u003cimg src=\"https://awesome.re/badge.svg\"\u003e\u003c/a\u003e\r\n  \u003ca href=\"https://arxiv.org/abs/2405.01466\"\u003e\u003cimg src=\"https://img.shields.io/badge/arXiv-2405.01466-blue.svg\"\u003e\u003c/a\u003e\r\n  \u003cimg src=\"https://img.shields.io/github/stars/iSEngLab/AwesomeLLM4APR?color=yellow\u0026label=Stars\"\u003e\r\n  \u003cimg src=\"https://img.shields.io/badge/PRs-Welcome-red\"\u003e\r\n  \u003cimg src=\"https://img.shields.io/github/last-commit/iSEngLab/AwesomeLLM4APR\"\u003e\r\n\u003c/p\u003e\r\n\r\n\r\n\r\n**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](https://github.com/iSEngLab/AwesomeLLM4APR/blob/main/update.md), or explore the curated summaries on our [summary site](https://iseabot.github.io/CI-LLM4APR).**\r\n\r\n## 📖 Contents\r\n\r\n- [👏 Citation](#-citation)\r\n- [💡 Repair Scenarios](#-repair-scenarios)\r\n  - [Semantic Bug](#semantic-bug)\r\n  - [Security Vulnerability](#security-vulnerability)\r\n  - [Syntax Error](#syntax-error)\r\n  - [Programming Problem](#programming-problem)\r\n  - [Static Warning](#static-warning)\r\n  - [Self-Debug](#self-debug)\r\n  - [Type Error](#type-error)\r\n  - [Web UI Test](#web-ui-test)\r\n  - [Repository-level Issue](#repository-level-issue)\r\n  - [Smart Contract](#smart-contract)\r\n  - [Hardware Bug](#hardware-bug)\r\n  - [Performance Bug](#performance-bug)\r\n  - [API Misuse](#api-misuse)\r\n  - [Formal Specification](#formal-specification)\r\n  - [Crash Bug](#crash-bug)\r\n  - [Test Case](#test-case)\r\n  - [Error-handling Bug](#error-handling-bug)\r\n  - [Formal Proof](#formal-proof)\r\n  - [Translation Bug](#translation-bug)\r\n  - [GitHub Issue](#github-issue)\r\n  - [Code Review](#code-review)\r\n  - [Motion Planner](#motion-planner)\r\n- [🙆 Human Study](#-human-study)\r\n- [🙅 Patch Correctness Assessment](#-patch-correctness-assessment)\r\n- [📊 Benchmark](#-benchmark)\r\n- [🤔 Related APR Surveys](#-related-apr-surveys)\r\n\r\n\r\n## 👏 Citation\r\n\r\n```bibtex\r\n@article{zhang2024survey,\r\n  title={A Systematic Literature Review on Large Language Models for Automated Program Repair},\r\n  author={Zhang, Quanjun and Fang, Chunrong and Xie, Yang and Ma, Yuxiang and Sun, Weisong and Yang, Yun and Chen, Zhenyu},\r\n  journal={arXiv preprint arXiv:2405.01466}\r\n  year={2024}\r\n}\r\n\r\n```\r\n\r\n\r\n## 🔥🔥 New Papers\r\n\r\n1. Divide-and-Conquer: Automating Code Revisions via Localization-and-Revision [2024-TOSEM] [[repo](https://zenodo.org/records/8373320)]\r\n2. Error Delayed Is Not Error Handled: Understanding and Fixing Propagated Error-Handling Bugs [2025-FSE/ESEC] [[repo](https://github.com/EH-Fixer/EH-Fixer)]\r\n3. An Empirical Evaluation of Pre-trained Large Language Models for Repairing Declarative Formal Specifications [2024-EMSE] [[repo](https://github.com/Mohannadcse/AlloySpecRepair)]\r\n4. Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing [2025-ASE] [[repo](https://sites.google.com/view/guirepair)]\r\n5. SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains? [2025-ICLR] [[repo](https://swebench.com/multimodal)]\r\n6. DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models [2025-ICSE] [[repo](https://github.com/UGAIForge/DesignRepair)]\r\n7. Combining Logic and Large Language Models for Assisted Debugging and Repair of ASP Programs [2025-ICST] [[repo](https://github.com/RicardoBrancas/formhe)]\r\n8. Less is More: Adaptive Program Repair with Bug Localization and Preference Learning [2025-AAAI] [[repo](https://github.com/zhenlongDai/)]\r\n9. Exploring Parameter-Efficient Fine-Tuning of Large Language Model on Automated Program Repair [2024-ASE] [[repo](https://github.com/zjulgc/llmpeft4apr)]\r\n10. FastFixer: An Efficient and Effective Approach for Repairing Programming Assignments [2024-ASE] [[repo](https://github.com/LiuFang816/FastFixer)]\r\n11. Investigating Large Language Models Capabilities for Automatic Code Repair in Python [2024-Cluster Computing] [[repo](https://github.com/KshitizBasnet2021/ChatGPTResearch)]\r\n12. Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization [2025-AAAI] [[repo](https://github.com/pmorvalho/LLM-CEGIS-Repair)]\r\n13. Code repair with llms gives an exploration-exploitation tradeoff [2024-NeurIPS] [[repo](https://github.com/haotang1995/REx)]\r\n14. Automated Program Repair for Introductory Programming Assignments [2024-TLT]\r\n15. Investigating the Transferability of Code Repair for Low-Resource Programming Languages [2025-NAACL] [[repo](https://github.com/KyleWong288/Distill_LRPL)]\r\n16. CREF: An LLM-based Conversational Software Repair Framework for Programming Tutors [2024-ISSTA] [[repo](https://github.com/buaabarty/CREF)]\r\n17. RePair: Automated Program Repair with Process-based Feedback [2024-ACL] [[repo](https://github.com/TnTWoW/RePair)]\r\n18. MASAI: Modular Architecture for Software-engineering AI Agents [2024-NeurIPS] \r\n19. CodeR: Issue Resolving with Multi-Agent and Task Graphs [2024-arxiv] [[repo](https://github.com/NL2Code/CodeR)]\r\n20. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering [2024-NeurIPS] [[repo](https://github.com/SWE-agent/SWE-agent)]\r\n21. AutoCodeRover: Autonomous Program Improvement [2024-ISSTA] [[repo](https://autocoderover.dev/)]\r\n22. MarsCode Agent: AI-native Automated Bug Fixing [2024-arxiv] \r\n23. Enhancing Automated Program Repair with Solution Design [2024-ASE] [[repo](https://figshare.com/s/82ed8e86e88d3268b4c1)]\r\n24. Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolution [2025-MSR] [[repo](https://anonymous.4open.science/r/prompt-knowledge-gap-BE45/README.md)]\r\n25. OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution [2025-ISSTA] [[repo](https://github.com/DeepSoftwareAnalytics/OmniGIRL)]\r\n26. SWE-GPT: A Process-Centric Language Model for Automated Software Improvement [2025-ISSTA] [[repo](https://github.com/LingmaTongyi/Lingma-SWE-GPT)]\r\n27. SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents [2025-NeurIPS] [[repo](https://github.com/logic-star-ai/SWT-Bench)]\r\n28. SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement [2025-ICLR] [[repo](https://github.com/aorwall/moatless-tree-search)]\r\n29. RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph [2025-ICLR] [[repo](https://github.com/ozyyshr/RepoGraph)]\r\n30. SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution [2025-NeurIPS] [[repo](https://github.com/facebookresearch/swe-rl)]\r\n31. Demystifying LLM-based Software Engineering Agents [2025-FSE/ESEC] [[repo](https://github.com/OpenAutoCoder/Agentless)]\r\n32. MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution [2025-NeurIPS]\r\n33. OpenHands: An Open Platform for AI Software Developers as Generalist Agents [2025-ICLR] [[repo](https://github.com/All-Hands-AI/OpenHands)]\r\n34. Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration [2025-FSE-Companion] [[repo](https://github.com/RepoUnderstander/RepoUnderstander)]\r\n35. A Case Study of LLM for Automated Vulnerability Repair: Assessing Impact of Reasoning and Patch Validation Feedback [2024-AIware] [[repo](https://drive.google.com/drive/folders/1yrYUJS1r2cu7G6D3ezASsfugrNqgwc3v)]\r\n36. VulAdvisor: Natural Language Suggestion Generation for Software Vulnerability Repair [2024-ASE] [[repo](https://github.com/zhangj111/VulAdvisor)]\r\n37. Teaching AI the ‘Why’ and ‘How’ of Software Vulnerability Fixes [2025-FSE/ESEC] [[repo](https://github.com/amiaog/Teaching-AI-the-Why-and-How-of-Software-Vulnerability-Fixes)]\r\n38. APPATCH: Automated Adaptive Prompting Large Language Models for Real-World Software Vulnerability Patching [2025-USENIX Security] [[repo](https://zenodo.org/records/14741018)]\r\n39. Closing the Gap: A User Study on the Real-world Usefulness of AI-powered Vulnerability Detection \u0026 Repair in the IDESecurityArtifact-FunctionalArtifact-AvailableArtifact-Reusable [2025-ICSE] [[repo](https://doi.org/10.6084/m9.figshare.26367139)]\r\n40. PATCHAGENT: A Practical Program Repair Agent Mimicking Human Expertise [2025-USENIX Security] [[repo](https://osf.io/8k2ac)]\r\n41. CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair [2024-ICLR]\r\n42. From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging [2024-arxiv] [[repo](https://github.com/YerbaPage/MGDebugger)]\r\n43. When Large Language Models Confront Repository-Level Automatic Program Repair: How Well They Done? [2024-ICSE] \r\n44. T5APR: Empowering Automated Program Repair across Languages through Checkpoint Ensemble [2024-JSS] [[repo](https://github.com/h4iku/T5APR)]\r\n45. A Deep Dive into Large Language Models for Automated Bug Localization and Repair [2024-FSE/ESEC] \r\n46. Benchmarking Automated Program Repair: An Extensive Study on Both Real-World and Artificial Bugs [2024-ISSTA]\r\n47. Automated Program Repair via Conversation: Fixing 162 out of 337 bugs for $0.42 each using chatgpt [2024-ISSTA]\r\n48. How Far Can We Go with Practical Function-Level Program Repair? [2024-arxiv] [[repo](https://github.com/GhabiX/SRepair)]\r\n49. Exploring and Lifting the Robustness of LLM-powered Automated Program Repair with Metamorphic Testing [2024-arxiv] \r\n50. Thinkrepair: Self-directed automated program repair [2024-ISSTA] [[repo](https://github.com/vinci-grape/ThinkRepair)]\r\n51. Hierarchical Knowledge Injection for Improving LLM-based Program Repair [2025-ASE] [[repo](https://github.com/SOAR-Lab/llm-apr-knowledge-injection)]\r\n52. Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repair [2025-TOSEM] [[repo](https://github.com/XYZboom/DEVLoRe)]\r\n53. APRMCTS: Improving LLM-based Automated Program Repair with Iterative Tree Search [2025-ASE] [[repo](https://github.com/Tomsawyerhu/APR-MCTS)]\r\n54. Demystifying Memorization in LLM-based Program Repair via a General Hypothesis Testing Framework [2025-FSE/ESEC] [[repo](https://sites.google.com/view/memprompt)]\r\n55. Hybrid Automated Program Repair by Combining Large Language Models and Program Analy [2025-TOSEM] [[repo](https://github.com/Feng-Jay/GiantRepair)]\r\n56. When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair [2025-TOSEM] [[repo](https://github.com/stringing/Federated-LLM-Based-APR)]\r\n57. The Impact of Fine-tuning Large Language Models on Automated Program Repair [2025-ICSME] [[repo](https://doi.org/10.5281/zenodo.16359186)]\r\n58. Knowledge-Enhanced Program Repair for Data Science Code [2025-ICSE] [[repo](https://github.com/ShuyinOuyang/DSrepair)]\r\n59. The Fact Selection Problem in LLM-Based Program Repair [2025-ICSE] [[repo](https://github.com/PyRepair/maniple)]\r\n60. The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models [2025-EASE] [[repo](https://doi.org/10.5281/zenodo.15294695)]\r\n61. MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning [2025-TOSEM] \r\n62. Adversarial Reasoning for Repair Based on Inferred Program Intent [2025-ISSTA] [[repo](https://doi.org/10.5281/zenodo.15367930)]\r\n63. Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair viaRepair Ingredients Search [2025-ICSE] [[repo](https://sites.google.com/view/repairingredients)]\r\n64. Aligning the Objective of LLM-based Program Repair [2025-ICSE] [[repo](https://github.com/CUHK-Shenzhen-SE/D4C)]\r\n65. One Size Does Not Fit All: Multi-granularity Patch Generation for Better Automated Program Repair [2024-ISSTA] [[repo](https://zenodo.org/records/12660892)]\r\n66. Template-Guided Program Repair in the Era of Large Language Models [2025-ICSE] [[repo](https://sites.google.com/view/neuraltemplaterepair)]\r\n67. Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models [2024-arxiv] [[repo](https://zenodo.org/records/10851256)]\r\n68. HapRepair: Learn to Repair OpenHarmony Apps [2025-FSE/ESEC] [[repo](https://github.com/SMAT-Lab/HapRepair)]\r\n69. CORE: Resolving Code Quality Issues using LLMs [2024-FSE/ESEC]\r\n70. FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair [2024-TSE] [[repo](https://github.com/TestingResearchIllinois/idoft)]\r\n71. NIODebugger: A Novel Approach to Repair Non-Idempotent-Outcome Tests with LLM-Based Agent [2025-ICSE] [[repo](https://github.com/zhenlongDai/)]\r\n72. RetypeR: Integrated Retrieval-based Automatic Program Repair for Python Type Errors [2024-ICSME] [[repo](https://anonymous.4open.science/r/RetypeR)]\r\n\r\n\r\n## 💡 Repair Scenarios \r\n\r\n### Semantic Bug\r\n\r\n1. From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging [2024-arxiv] [[repo](https://github.com/YerbaPage/MGDebugger)]\r\n2. When Large Language Models Confront Repository-Level Automatic Program Repair: How Well They Done? [2024-ICSE] \r\n3. T5APR: Empowering Automated Program Repair across Languages through Checkpoint Ensemble [2024-JSS] [[repo](https://github.com/h4iku/T5APR)]\r\n4. A Deep Dive into Large Language Models for Automated Bug Localization and Repair [2024-FSE/ESEC] \r\n5. Benchmarking Automated Program Repair: An Extensive Study on Both Real-World and Artificial Bugs [2024-ISSTA] [[repo](N.A)]\r\n6. Automated Program Repair via Conversation: Fixing 162 out of 337 bugs for $0.42 each using chatgpt [2024-ISSTA] [[repo](N.A)]\r\n7. How Far Can We Go with Practical Function-Level Program Repair? [2024-arxiv] [[repo](https://github.com/GhabiX/SRepair)]\r\n8. Exploring and Lifting the Robustness of LLM-powered Automated Program Repair with Metamorphic Testing [2024-arxiv] \r\n9. Thinkrepair: Self-directed automated program repair [2024-ISSTA] [[repo](https://github.com/vinci-grape/ThinkRepair)]\r\n10. Hierarchical Knowledge Injection for Improving LLM-based Program Repair [2025-ASE] [[repo](https://github.com/SOAR-Lab/llm-apr-knowledge-injection)]\r\n11. Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repair [2025-TOSEM] [[repo](https://github.com/XYZboom/DEVLoRe)]\r\n12. APRMCTS: Improving LLM-based Automated Program Repair with Iterative Tree Search [2025-ASE] [[repo](https://github.com/Tomsawyerhu/APR-MCTS)]\r\n13. Demystifying Memorization in LLM-based Program Repair via a General Hypothesis Testing Framework [2025-FSE/ESEC] [[repo](https://sites.google.com/view/memprompt)]\r\n14. Hybrid Automated Program Repair by Combining Large Language Models and Program Analy [2025-TOSEM] [[repo](https://github.com/Feng-Jay/GiantRepair)]\r\n15. When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair [2025-TOSEM] [[repo](https://github.com/stringing/Federated-LLM-Based-APR)]\r\n16. The Impact of Fine-tuning Large Language Models on Automated Program Repair [2025-ICSME] [[repo](https://doi.org/10.5281/zenodo.16359186)]\r\n17. Knowledge-Enhanced Program Repair for Data Science Code [2025-ICSE] [[repo](https://github.com/ShuyinOuyang/DSrepair)]\r\n18. The Fact Selection Problem in LLM-Based Program Repair [2025-ICSE] [[repo](https://github.com/PyRepair/maniple)]\r\n19. The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models [2025-EASE] [[repo](https://doi.org/10.5281/zenodo.15294695)]\r\n20. MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning [2025-TOSEM] \r\n21. Adversarial Reasoning for Repair Based on Inferred Program Intent [2025-ISSTA] [[repo](https://doi.org/10.5281/zenodo.15367930)]\r\n22. Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair viaRepair Ingredients Search [2025-ICSE] [[repo](https://sites.google.com/view/repairingredients)]\r\n23. Aligning the Objective of LLM-based Program Repair [2025-ICSE] [[repo](https://github.com/CUHK-Shenzhen-SE/D4C)]\r\n24. One Size Does Not Fit All: Multi-granularity Patch Generation for Better Automated Program Repair [2024-ISSTA] [[repo](https://zenodo.org/records/12660892)]\r\n25. Template-Guided Program Repair in the Era of Large Language Models [2025-ICSE] [[repo](https://sites.google.com/view/neuraltemplaterepair)]\r\n26. Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models [2024-arxiv] [[repo](https://zenodo.org/records/10851256)]\r\n27. HapRepair: Learn to Repair OpenHarmony Apps [2025-FSE/ESEC] [[repo](https://github.com/SMAT-Lab/HapRepair)]\r\n28. Automated program repair for variability bugs in software product line systems[2024-JSS] [[paper](https://www.sciencedirect.com/science/article/abs/pii/S0164121224001973)]\r\n29. A Unified Debugging Approach via LLM-Based Multi-Agent Synergy [2024-arxiv] [[paper](https://arxiv.org/pdf/2404.17153)] [[repo](https://github.com/afortunado-aceptado/Rudra)]\r\n30. How Far Can We Go with Practical Function-Level Program Repair? [2024-arxiv] [[paper](https://arxiv.org/pdf/2404.12833)] [[repo](https://github.com/GhabiX/SRepair)]\r\n31. Automated program repair via conversation: Fixing 162 out of 337 bugs for $0.42 each using chatgpt[2024-ISSTA] [[paper](https://dl.acm.org/doi/10.1145/3650212.3680323)]\r\n   \u003cbr\u003e Old Version: Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT [2023-arxiv] [[paper](https://arxiv.org/pdf/2304.00385)]\r\n32. A Novel Approach for Automatic Program Repair using Round-Trip Translation with Large Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2401.07994)] [[repo](https://zenodo.org/records/10500594)]\r\n33. Out of Context: How important is Local Context in Neural Program Repair? [2024-ICSE] [[paper](https://arxiv.org/pdf/2312.04986)] [[repo](https://github.com/giganticode/out_of_context_paper_data)]\r\n34. Multi-Objective Fine-Tuning for Enhanced Program Repair with LLMs [2024-arxiv] [[paper](https://arxiv.org/pdf/2404.12636)]\r\n35. Aligning the Objective of LLM-based Program Repair [2025-ICSE] [[paper](https://arxiv.org/pdf/2404.08877)] [[repo](https://github.com/CUHK-Shenzhen-SE/D4C)]\r\n36. ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs [2024-arxiv] [[paper](https://arxiv.org/pdf/2403.01971)]\r\n37. Exploring the Potential of Pre-Trained Language Models of Code for Automated Program Repair [2024-Electronics] [[paper](https://www.mdpi.com/2079-9292/13/7/1200)]\r\n38. CigaR: Cost-efficient Program Repair with LLMs [2024-arxiv] [[paper](https://arxiv.org/pdf/2402.06598)] [[repo](https://github.com/ASSERT-KTH/cigar)]\r\n39. The Fact Selection Problem in LLM-Based Program Repair [2024-arxiv] [[paper](https://arxiv.org/pdf/2404.05520)] [[repo](https://github.com/PyRepair/maniple)]\r\n40. A Novel Approach for Automated Program Repair using Round-Trip Translation with Large Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2401.07994)] [[repo](https://zenodo.org/records/10500594)]\r\n41. RepairAgent: An Autonomous, LLM-Based Agent for Program Repair [2024-arxiv] [[paper](https://arxiv.org/pdf/2403.17134)]\r\n42. A Deep Dive into Large Language Models for Automated Bug Localization and Repair [2024-FSE/ESEC] [[paper](https://arxiv.org/pdf/2404.11595)]\r\n43. Automated Program Repair in the Era of Large Pre-trained Language Models [2023-ICSE] [[paper](https://web.eecs.umich.edu/~movaghar/IEEE-2023-Automated_Program_Repair_in_the_Era_of_Large_Pre-trained_Language_Models.pdf)] [[repo](https://zenodo.org/records/7592886)]\r\n44. Repair Is Nearly Generation: Multilingual Program Repair with LLMs [2023-AAAI] [[paper](https://ojs.aaai.org/index.php/AAAI/article/download/25642/25414)]\r\n45. Retrieval-based prompt selection for code-related few-shot learning [2023-ICSE] [[paper](https://nashid.github.io/resources/papers/cedar-icse23.pdf)] [[repo](https://github.com/prompt-learning/cedar)]\r\n46. What makes good in-context demonstrations for code intelligence tasks with llms? [2023-ASE] [[paper](https://ieeexplore.ieee.org/abstract/document/10298329)] [[repo](https://github.com/shuzhenggao/ICL4code)]\r\n47. Fully Autonomous Programming with Large Language Models [2023-GECCO] [[paper](https://dl.acm.org/doi/pdf/10.1145/3583131.3590481)] [[repo](https://github.com/KoutchemeCharles/aied2023)]\r\n48. Automated Program Repair Using Generative Models for Code Infilling [2023-AIED] [[paper](https://link.springer.com/chapter/10.1007/978-3-031-36272-9_74)] [[repo](https://github.com/KoutchemeCharles/aied2023)]\r\n49. STEAM: Simulating the InTeractive BEhavior of ProgrAMmers for Automatic Bug Fixing [2023-arxiv] [[paper](https://arxiv.org/pdf/2308.14460)]\r\n50. Conversational automated program repair [2023-arxiv] [[paper](https://arxiv.org/pdf/2301.13246)]\r\n51. Is ChatGPT the Ultimate Programming Assistant--How far is it? [2023-arxiv] [[paper](https://arxiv.org/pdf/2304.11938)] [[repo](https://github.com/HaoyeTianCoder/ChatGPT-Study)]\r\n52. Using Large Language Models for Bug Localization and Fixing [2023-iCAST] [[paper](https://u-aizu.ac.jp/~markov/pubs/iCAST_23.pdf)]\r\n53. An Empirical Study on Fine-Tuning Large Language Models of Code for Automated Program Repair [2023-ASE] [[paper](https://ieeexplore.ieee.org/abstract/document/10298532)] [[repo](https://github.com/LLMC-APR/STUDY)]\r\n54. An Evaluation of the Effectiveness of OpenAI's ChatGPT for Automated Python Program Bug Fixing using QuixBugs [2023-iSEMANTIC] [[paper](https://ieeexplore.ieee.org/abstract/document/10295323)]\r\n55. Explainable Automated Debugging via Large Language Model-driven Scientific Debugging [2023-arxiv] [[paper](https://arxiv.org/pdf/2304.02195)]\r\n56. The Right Prompts for the Job: Repair Code-Review Defects with Large Language Model [2023-arxiv] [[paper](https://arxiv.org/pdf/2312.17485)]\r\n57. Impact of Code Language Models on Automated Program Repair [2023-ICSE] [[paper](https://arxiv.org/pdf/2302.05020)] [[repo](https://github.com/lin-tan/clm)]\r\n58. Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions [2023-arxiv] [[paper](https://arxiv.org/pdf/2304.03816)]\r\n59. The Plastic Surgery Hypothesis in the Era of Large Language Models [2023-ASE] [[paper](https://ieeexplore.ieee.org/abstract/document/10298499)] [[repo](https://zenodo.org/records/8244813)]\r\n60. Exploring the Limits of ChatGPT in Software Security Applications [2023-arxiv] [[paper](https://arxiv.org/pdf/2312.05275)]\r\n61. CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation [2023-arxiv] [[paper](https://arxiv.org/pdf/2311.08588)] [[repo](https://github.com/WeixiangYAN/CodeScope)]\r\n62. Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering [2023-arxiv] [[paper](https://lsiddiqsunny.github.io/public/2304.07840.pdf)] [[repo](https://zenodo.org/records/8122636)]\r\n63. Training Language Models for Programming Feedback Using Automated Repair Tools [2023-AIED] [[paper](https://research.aalto.fi/files/130373931/Training_Language_Models_for_Programming_Feedback_Using_Automated_Repair_Tools.pdf)] [[repo](https://github.com/KoutchemeCharles/aied2023)]\r\n64. RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair [2023-arxiv] [[paper](https://arxiv.org/pdf/2312.15698)] [[repo](https://anonymous.4open.science/r/repairllama-BC13)]\r\n65. Automated Code Editing with Search-Generate-Modify [2023-arxiv] [[paper](https://arxiv.org/pdf/2306.06490)] [[repo](https://github.com/SarGAMTEAM/SarGAM.git)]\r\n66. RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair [2023-FSE/ESEC] [[paper](https://arxiv.org/pdf/2309.06057)] [[repo](https://figshare.com/s/a4e95baee01bba14bf4b)]\r\n67. Neural Program Repair with Program Dependence Analysis and Effective Filter Mechanism [2023-arxiv] [[paper](https://arxiv.org/pdf/2305.09315)]\r\n68. Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback [2023-arxiv] [[paper](https://arxiv.org/pdf/2311.07215)] [[repo](https://github.com/Lune-Blue/COFFEE)]\r\n69. A study on Prompt Design, Advantages and Limitations of ChatGPT for Deep Learning Program Repair [2023-arxiv]  [[paper](https://arxiv.org/pdf/2304.08191)]\r\n70. Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair [2023-FSE/ESEC] [[paper](https://arxiv.org/pdf/2309.00608)] [[repo](https://github.com/ise-uiuc/Repilot)]\r\n71. Gamma: Revisiting Template-Based Automated Program Repair Via Mask Prediction [2023-ASE] [[paper](https://arxiv.org/pdf/2309.09308)] [[repo](https://github.com/iSEngLab/GAMMA)]\r\n72. An Extensive Study on Model Architecture and Program Representation in the Domain of Learning-based Automated Program Repair [2023-APR] [[paper](https://ieeexplore.ieee.org/abstract/document/10189328)] [[repo](https://github.com/AAI-USZ/APR23-representations)]\r\n73. Improving Automated Program Repair with Domain Adaptation [2023-TOSEM] [[paper](https://arxiv.org/pdf/2212.11414)] [[repo](https://github.com/arminzirak/TFix)]\r\n74. Enhancing Code Language Models for Program Repair by Curricular Fine-tuning Framework [2023-ICSME] [[paper](https://ieeexplore.ieee.org/abstract/document/10336339)]\r\n75. The potential use of ChatGPT for debugging and bug fixing [2023-] [[paper](https://oulurepo.oulu.fi/bitstream/handle/10024/44572/nbnfi-fe20231006139025.pdf?sequence=1)]\r\n76. CIRCLE: Continual Repair across Programming Languages [2022-ISSTA] [[paper](https://arxiv.org/pdf/2205.10956)] [[repo](https://github.com/2022CIRCLE/CIRCLE)]\r\n77. Towards JavaScript program repair with Generative Pre-trained Transformer (GPT-2) [2022-APR] [[paper](http://publicatio.bibl.u-szeged.hu/25241/1/Lajko-APR22.pdf)] [[repo](https://github.com/AAI-USZ/APR22-JS-GPT)]\r\n78. Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar [2022-ICLR] [[paper](https://arxiv.org/pdf/2204.06643)]\r\n79. Patch Generation with Language Models: Feasibility and Scaling Behavior [2022-ICLR] [[paper](https://openreview.net/pdf?id=rHlzJh_b1-5)]\r\n80. Can OpenAI's codex fix bugs?: an evaluation on QuixBugs [2022-APR] [[paper](https://dl.acm.org/doi/abs/10.1145/3524459.3527351)]\r\n81. An Analysis of the Automatic Bug Fixing Performance of ChatGPT [2022-APR] [[paper](https://ieeexplore.ieee.org/abstract/document/10189263)] [[repo](https://gitlab.rlp.net/dsobania/chatgpt-apr)]\r\n82. Less training, more repairing please: revisiting automated program repair via zero-shot learning [2022-FSE/ESEC] [[paer](https://dl.acm.org/doi/pdf/10.1145/3540250.3549101)] [[repo](https://zenodo.org/records/6819444)]\r\n83. Framing Program Repair as Code Completion [2022-APR] [[paper](http://repositorio.inesctec.pt/bitstreams/2fb3b152-a3ba-4561-ad11-3869b0d245a0/download)] [[repo](https://github.com/FranciscoRibeiro/code-truncater)]\r\n84. DEAR A Novel Deep Learning-based Approach for Automated Program Repair [2022-ICSE] [[paper](https://dl.acm.org/doi/pdf/10.1145/3510003.3510177)] [[repo](https://github.com/AutomatedProgramRepair-2021/dear-auto-fix)]\r\n85. Generating Bug-Fixes Using Pretrained Transformers [2021-PLDI] [[paper](https://arxiv.org/pdf/2104.07896)]\r\n86. Applying CodeBERT for Automated Program Repair of Java Simple Bugs [2021-MSR] [[paper](https://arxiv.org/pdf/2103.11626)] [[repo](https://github.com/EhsanMashhadi/MSR2021-ProgramRepair)]\r\n87. CURE Code-Aware Neural Machine Translation for Automatic Program Repair [2021-ICSE] [[paper](https://arxiv.org/pdf/2103.00073)] [[repo](https://github.com/lin-tan/CURE)]\r\n88. How to Understand Whole Software Repository? [2024-arXiv] [[paper](https://arxiv.org/pdf/2406.01422)]\r\n\r\n### Security Vulnerability\r\n\r\n1. One Size Does Not Fit All: Multi-granularity Patch Generation for Better Automated Program Repair [2024-ISSTA] [[repo](https://zenodo.org/records/12660892)]\r\n2. Template-Guided Program Repair in the Era of Large Language Models [2025-ICSE] [[repo](https://sites.google.com/view/neuraltemplaterepair)]\r\n3. A Case Study of LLM for Automated Vulnerability Repair: Assessing Impact of Reasoning and Patch Validation Feedback [2024-AIware] [[repo](https://drive.google.com/drive/folders/1yrYUJS1r2cu7G6D3ezASsfugrNqgwc3v)]\r\n4. VulAdvisor: Natural Language Suggestion Generation for Software Vulnerability Repair [2024-ASE] [[repo](https://github.com/zhangj111/VulAdvisor)]\r\n5. Teaching AI the ‘Why’ and ‘How’ of Software Vulnerability Fixes [2025-FSE/ESEC] [[repo](https://github.com/amiaog/Teaching-AI-the-Why-and-How-of-Software-Vulnerability-Fixes)]\r\n6. APPATCH: Automated Adaptive Prompting Large Language Models for Real-World Software Vulnerability Patching [2025-USENIX Security] [[repo](https://zenodo.org/records/14741018)]\r\n7. Closing the Gap: A User Study on the Real-world Usefulness of AI-powered Vulnerability Detection \u0026 Repair in the IDESecurityArtifact-FunctionalArtifact-AvailableArtifact\r\n8. Reusable [2025-ICSE] [[repo](https://doi.org/10.6084/m9.figshare.26367139)]\r\n9. PATCHAGENT: A Practical Program Repair Agent Mimicking Human Expertise [2025-USENIX Security] [[repo](https://osf.io/8k2ac)]\r\n10. 🔥Automated Repair of AI Code with Large Language Models and Formal Verification [2024-arXiv] [[paper](https://arxiv.org/abs/2405.08848)]\r\n11. 🔥NAVRepair: Node-type Aware C/C++ Code Vulnerability Repair [2024-arxiv] [[paper](https://arxiv.org/abs/2405.04994)]\r\n12. Enhanced Automated Code Vulnerability Repair using Large Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2401.03741)]\r\n13. Out of Sight, Out of Mind: Better Automatic Vulnerability Repair by Broadening Input Ranges and Sources [2024-ICSE] [[paper](https://dl.acm.org/doi/pdf/10.1145/3597503.3639222)] [[repo](https://github.com/soarsmu/VulMaster_)]\r\n14. A Study of Vulnerability Repair in JavaScript Programs with Large Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2403.13193)] [[repo](https://doi.org/10.5281/zenodo.10783763)]\r\n15. Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities [2024-arxiv] [[paper](https://arxiv.org/pdf/2402.17230)]\r\n16. Pre-trained Model-based Automated Software Vulnerability Repair: How Far are We? [2023-TDSC] [[paper](https://arxiv.org/pdf/2308.12533)] [[repo](https://github.com/iSEngLab/LLM4VulFix)]\r\n17. Examining zero-shot vulnerability repair with large language models [2023-S\u0026P] [[paper](https://arxiv.org/pdf/2112.02125)] [[repo](https://drive.google.com/drive/folders/1xJ-z2Wvvg7JSaxfTQdxayXFEmoF3y0ET?usp=sharing)]\r\n18. An Empirical Study on Fine-Tuning Large Language Models of Code for Automated Program Repair [2023-ASE] [[paper](https://ieeexplore.ieee.org/abstract/document/10298532)] [[repo](https://github.com/LLMC-APR/STUDY)]\r\n19. A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification [2023-arxiv] [[paper](https://arxiv.org/pdf/2305.14752)]\r\n20. Exploring the Limits of ChatGPT in Software Security Applications [2023-arxiv] [[paper](https://arxiv.org/pdf/2312.05275)]\r\n21. ZeroLeak: Using LLMs for Scalable and Cost Effective Side-Channel Patching [2023-arxiv] [[paper](https://arxiv.org/pdf/2308.13062)]\r\n22. How ChatGPT is Solving Vulnerability Management Problem [2023-arxiv] [[paper](https://arxiv.org/pdf/2311.06530)] [[repo](https://anonymous.4open.science/r/DefectManagementEvaluation-0411)]\r\n23. How Effective Are Neural Networks for Fixing Security Vulnerabilities [2023-ISSTA] [[paper](https://dl.acm.org/doi/pdf/10.1145/3597926.3598135)] [[repo](https://github.com/lin-tan/llm-vul)]\r\n24. Vision Transformer-Inspired Automated Vulnerability Repair [2023-TOSEM] [[paper](https://www.researchgate.net/profile/Michael-Fu-8/publication/375618720_Vision_Transformer-Inspired_Automated_Vulnerability_Repair/links/65a9b875ee1e1951fbbe6538/Vision-Transformer-Inspired-Automated-Vulnerability-Repair.pdf)] [[repo](https://github.com/awsm-research/VQM)]\r\n25. Can large language models find and fix vulnerable software? [2023-arxiv] [[paper](https://arxiv.org/pdf/2308.10345)]\r\n26. VulRepair: A T5-Based Automated Software Vulnerability Repair [2022-FSE/ESEC] [[paper](https://www.researchgate.net/profile/Chakkrit-Tantithamthavorn/publication/362092639_VulRepair_A_T5-Based_Automated_Software_Vulnerability_Repair/links/6345ea1076e39959d6b73228/VulRepair-A-T5-Based-Automated-Software-Vulnerability-Repair.pdf)] [[repo](https://github.com/awsm-research/VulRepair)]\r\n\r\n    \r\n\r\n### Syntax Error\r\n\r\n1. HapRepair: Learn to Repair OpenHarmony Apps [2025-FSE/ESEC] [[repo](https://github.com/SMAT-Lab/HapRepair)]\r\n2. A Novel Approach for Automated Program Repair using Round-Trip Translation with Large Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2401.07994)] [[repo](https://zenodo.org/records/10500594)]\r\n3. Repair Is Nearly Generation: Multilingual Program Repair with LLMs [2023-AAAI] [[paper](https://ojs.aaai.org/index.php/AAAI/article/download/25642/25414)]\r\n4. Fixing Rust Compilation Errors using LLMs [2023-arxiv] [[paper](https://arxiv.org/pdf/2308.05177)]\r\n5. An Empirical Study on Fine-Tuning Large Language Models of Code for Automated Program Repair [2023-ASE] [[paper](https://ieeexplore.ieee.org/abstract/document/10298532)] [[repo](https://github.com/LLMC-APR/STUDY)]\r\n6. A Chain of AI-based Solutions for Resolving FQNs and Fixing Syntax Errors in Partial Code [2023-arxiv] [[paper](https://arxiv.org/pdf/2306.11981)] [[repo](https://github.com/SE-qinghuang/A-Chain-of-AI-based-Solutions-for-Resolving-FQNs-and-Fixing-Syntax-Errors-in-Partial-Code)]\r\n7. The Right Prompts for the Job: Repair Code-Review Defects with Large Language Model [2023-arxiv] [[paper](https://arxiv.org/pdf/2312.17485)]\r\n8. SYNSHINE: improved fixing of Syntax Errors [2022-TSE] [[paper](https://ieeexplore.ieee.org/abstract/document/9913705)] [[repo](https://zenodo.org/record/4572390#.Y4CY8xRByUk)]\r\n\r\n### Programming Problem\r\n\r\n1. 🔥Combining Logic and Large Language Models for Assisted Debugging and Repair of ASP Programs [2025-ICST] [[repo](https://github.com/RicardoBrancas/formhe)]\r\n2. 🔥Less is More: Adaptive Program Repair with Bug Localization and Preference Learning [2025-AAAI] [[repo](https://github.com/zhenlongDai/)]\r\n3. 🔥Exploring Parameter-Efficient Fine-Tuning of Large Language Model on Automated Program Repair [2024-ASE] [[repo](https://github.com/zjulgc/llmpeft4apr)]\r\n4. 🔥FastFixer: An Efficient and Effective Approach for Repairing Programming Assignments [2024-ASE] [[repo](https://github.com/LiuFang816/FastFixer)]\r\n5. 🔥Investigating Large Language Models Capabilities for Automatic Code Repair in Python [2024-Cluster Computing] [[repo](https://github.com/KshitizBasnet2021/ChatGPTResearch)]\r\n6. 🔥Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization [2025-AAAI] [[repo](https://github.com/pmorvalho/LLM-CEGIS-Repair)]\r\n7. 🔥Code repair with llms gives an exploration-exploitation tradeoff [2024-NeurIPS] [[repo](https://github.com/haotang1995/REx)]\r\n8. 🔥Automated Program Repair for Introductory Programming Assignments [2024-TLT] [[repo](N.A)]\r\n9. 🔥Investigating the Transferability of Code Repair for Low-Resource Programming Languages [2025-NAACL] [[repo](https://github.com/KyleWong288/Distill_LRPL)]\r\n10. 🔥CREF: An LLM-based Conversational Software Repair Framework for Programming Tutors [2024-ISSTA] [[repo](https://github.com/buaabarty/CREF)]\r\n11. 🔥RePair: Automated Program Repair with Process-based Feedback [2024-ACL] [[repo](https://github.com/TnTWoW/RePair)]\r\n12. 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](https://arxiv.org/abs/2409.12993)]\r\n13. A Unified Debugging Approach via LLM-Based Multi-Agent Synergy [2024-arXiv] [[paper](https://arxiv.org/pdf/2404.17153)] [[repo](https://github.com/afortunado-aceptado/Rudra)]\r\n14. PyDex: Repairing Bugs in Introductory Python Assignments using LLMs [2024-OOPSLA] [[paper](https://dl.acm.org/doi/pdf/10.1145/3649850)] [[repo](https://github.com/microsoft/prose-benchmarks/tree/main/PyDex)]\r\n15. DebugBench: Evaluating Debugging Capability of Large Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2401.04621)] [[repo](https://github.com/thunlp/DebugBench)]\r\n16. ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs [2024-arxiv] [[paper](https://arxiv.org/pdf/2403.01971)]\r\n17. ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair [2024-arxiv] [[paper](https://arxiv.org/pdf/2310.16253)] [[repo](https://github.com/appmlk/ConDefects)]\r\n18. Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments [2024-arxiv] [[paper](https://arxiv.org/pdf/2404.01754)]\r\n19. Improved Program Repair Methods using Refactoring with GPT Models [2024-SIGCSE TS] [[paper](https://dl.acm.org/doi/pdf/10.1145/3626252.3630875)] [[repo](https://github.com/RYOSKATE/refactory-with-gpt)]\r\n20. A critical review of large language model on software engineering: An example from chatgpt and automated program repair [2023-arxiv] [[paper](https://arxiv.org/pdf/2310.08879)] [[repo](https://github.com/iSEngLab/EvalGPTFix)]\r\n21. Automated Repair of Programs from Large Language Models [2023-ICSE] [[paper](https://arxiv.org/pdf/2205.10583)] [[repo](https://github.com/zhiyufan/apr4codex)]\r\n22. FixEval: Execution-based Evaluation of Program Fixes for Programming Problems [2023-APR] [[paper](https://arxiv.org/pdf/2206.07796)] [[repo](https://github.com/mahimanzum/FixEval)]\r\n23. Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues [2023-TOSEM] [[paper](https://dl.acm.org/doi/pdf/10.1145/3643674)] [[repo](https://github.com/yueyueL/ChatGPT-CodeGenAnalysis)]\r\n24. Repairing bugs in python assignments using large language models [2022-arixv] [[paper](https://arxiv.org/pdf/2209.14876)]\r\n\r\n### Static Warning\r\n\r\n1. CORE: Resolving Code Quality Issues using LLMs [2024-FSE/ESEC]\r\n2. Frustrated with Code Quality Issues? LLMs can Help! [2024-FSE/ESEC] [[paper](https://arxiv.org/pdf/2309.12938)] [[repo](https://aka.ms/CORE_MSRI)]\r\n3. SkipAnalyzer: An Embodied Agent for Code Analysis with Large Language Models [2023-arxiv] [[paper](https://arxiv.org/pdf/2310.18532)] [[repo](https://zenodo.org/records/10043170)]\r\n4. RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair [2023-FSE/ESEC] [[paper](https://arxiv.org/pdf/2309.06057)] [[repo](https://figshare.com/s/a4e95baee01bba14bf4b)]\r\n5. InferFix: End-to-End Program Repair with LLMs over Retrieval-Augmented Prompts [2023-FSE/ESEC] [[paper](https://arxiv.org/pdf/2303.07263)] [[repo](https://github.com/microsoft/InferredBugs)]\r\n6. Can LLMs Patch Security Issues [2023-arxiv] [[paper](https://arxiv.org/html/2312.00024v2)] [[repo](https://github.com/Kamel773/LLM-code-refine)]\r\n7. Improving Automated Program Repair with Domain Adaptation [2023-TOSEM] [[paper](https://arxiv.org/pdf/2212.11414)] [[repo](https://github.com/arminzirak/TFix)]\r\n8. An empirical study of deep transfer learning-based program repair for Kotlin projects [2022-FSE/ESEC] [[paper](https://dl.acm.org/doi/abs/10.1145/3540250.3558967)]\r\n9. TFix-Learning to Fix Coding Errors with a Text-to-Text Transformer [2021-PMLR] [[paper](http://proceedings.mlr.press/v139/berabi21a/berabi21a.pdf)] [[repo](https://github.com/eth-sri/TFix)]\r\n\r\n### Self-Debug\r\n\r\n1. Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models [2024-arxiv] [[repo](https://zenodo.org/records/10851256)]\r\n2. CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair [2024-ICLR]\r\n3. From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging [2024-arXiv] [[paper](https://arxiv.org/abs/2410.01215)] [[repo](https://github.com/YerbaPage/MGDebugger)]\r\n4. Teaching Large Language Models to Self-Debug [2024-ICLR] [[paper](https://arxiv.org/pdf/2304.05128)]\r\n5. OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement [2024-arxiv] [[paper](https://arxiv.org/pdf/2402.14658)] [[repo](https://github.com/OpenCodeInterpreter/OpenCodeInterpreter)]\r\n6. CYCLE: Learning to Self-Refine the Code Generation [2024-OOPSLA] [[paper](https://arxiv.org/pdf/2403.18746)] [[repo](https://github.com/ARiSE-Lab/CYCLE_OOPSLA_24)]\r\n7. LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step [2024-arxiv] [[paper](https://arxiv.org/pdf/2402.16906)] [[repo](https://github.com/FloridSleeves/LLMDebugger)]\r\n8. Leveraging Print Debugging to Improve Code Generation in Large Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2401.05319)]\r\n9. SelfEvolve: A Code Evolution Framework via Large Language Models [2023-arxiv] [[paper](https://arxiv.org/pdf/2306.02907)]\r\n10. Self-Refine: Iterative Refinement with Self-Feedback [2023-NeurIPS] [[paper](https://proceedings.neurips.cc/paper_files/paper/2023/file/91edff07232fb1b55a505a9e9f6c0ff3-Paper-Conference.pdf)] [[repo](https://github.com/madaan/self-refine)]\r\n11. AgentCoder: Multi Agent-Code Generation with Iterative Testing and Optimisation [2023-arxiv] [[paper](https://arxiv.org/pdf/2312.13010)]\r\n12. Self-Edit: Fault-Aware Code Editor for Code Generation [2023-ACL] [[paper](https://arxiv.org/pdf/2305.04087)] [[repo](https://github.com/zkcpku/Self-Edit)]\r\n13. Is Self-Repair a Silver Bullet for Code Generation? [2023-ICLR] [[paper](https://openreview.net/pdf?id=y0GJXRungR)] [[repo](https://github.com/theoxo/self-repair)]\r\n\r\n\r\n### Type Error\r\n\r\n1. RetypeR: Integrated Retrieval-based Automatic Program Repair for Python Type Errors [2024-ICSME] [[repo](https://anonymous.4open.science/r/RetypeR)]\r\n2. Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Errors [2024-ICSE] [[paper](https://arxiv.org/pdf/2306.01394)] [[repo](https://github.com/JohnnyPeng18/TypeFix)]\r\n3. PyTy: Repairing Static Type Errors in Python [2024-ICSE] [[paper](https://arxiv.org/pdf/2401.06619)] [[repo](https://github.com/sola-st/PyTy)]\r\n4. GPT-3-Powered Type Error Debugging: Investigating the Use of Large Language Models for Code Repair [2023-SLE] [[paper](https://dl.acm.org/doi/abs/10.1145/3623476.3623522)] [[repo](https://gitlab.com/FranciscoRibeiro/mentat)]\r\n\r\n### Web UI Test\r\n\r\n1. Guiding ChatGPT to Fix Web UI Tests via Explanation-Consistency Checking [2023-arxiv] [[paper](https://arxiv.org/pdf/2312.05778)]\r\n\r\n### Repository-level Issue\r\n\r\n1. MASAI: Modular Architecture for Software-engineering AI Agents [2024-NeurIPS] \r\n2. CodeR: Issue Resolving with Multi-Agent and Task Graphs [2024-arxiv] [[repo](https://github.com/NL2Code/CodeR)]\r\n3. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering [2024-NeurIPS] [[repo](https://github.com/SWE-agent/SWE-agent)]\r\n4. AutoCodeRover: Autonomous Program Improvement [2024-ISSTA] [[repo](https://autocoderover.dev/)]\r\n5. MarsCode Agent: AI-native Automated Bug Fixing [2024-arxiv] \r\n6. Enhancing Automated Program Repair with Solution Design [2024-ASE] [[repo](https://figshare.com/s/82ed8e86e88d3268b4c1)]\r\n7. Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolution [2025-MSR] [[repo](https://anonymous.4open.science/r/prompt-knowledge-gap-BE45/README.md)]\r\n8. OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution [2025-ISSTA] [[repo](https://github.com/DeepSoftwareAnalytics/OmniGIRL)]\r\n9. SWE-GPT: A Process-Centric Language Model for Automated Software Improvement [2025-ISSTA] [[repo](https://github.com/LingmaTongyi/Lingma-SWE-GPT)]\r\n10. SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents [2025-NeurIPS] [[repo](https://github.com/logic-star-ai/SWT-Bench)]\r\n11. SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement [2025-ICLR] [[repo](https://github.com/aorwall/moatless-tree-search)]\r\n12. RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph [2025-ICLR] [[repo](https://github.com/ozyyshr/RepoGraph)]\r\n13. SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution [2025-NeurIPS] [[repo](https://github.com/facebookresearch/swe-rl)]\r\n14. Demystifying LLM-based Software Engineering Agents [2025-FSE/ESEC] [[repo](https://github.com/OpenAutoCoder/Agentless)]\r\n15. MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution [2025-NeurIPS] [[repo](N.A)]\r\n16. OpenHands: An Open Platform for AI Software Developers as Generalist Agents [2025-ICLR] [[repo](https://github.com/All-Hands-AI/OpenHands)]\r\n17. Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration [2025-FSE-Companion] [[repo](https://github.com/RepoUnderstander/RepoUnderstander)]\r\n\r\n### Smart Contract\r\n\r\n1. ACFIX: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contracts [2024-arxiv] [[paper](https://arxiv.org/pdf/2403.06838)]\r\n2. Evaluating ChatGPT for Smart Contracts Vulnerability Correction [2023-COMPSAC] [[paper](https://ieeexplore.ieee.org/abstract/document/10197134)] [[repo](https://github.com/enaples/solgpt)]\r\n\r\n### Hardware Bug\r\n\r\n1. CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair [2024-ICLR]\r\n2. On Hardware Security Bug Code Fixes By Prompting Large Language Models [2024-TIFS] [[paper](https://ieeexplore.ieee.org/abstract/document/10462177)] [[repo](https://zenodo.org/records/10416865)]\\\r\n   Its pre-print: Fixing Hardware Security Bugs with Large Language Models [2022-arXiv] [[paper](https://arxiv.org/abs/2302.01215)]\r\n3. HDLdebugger: Streamlining HDL debugging with Large Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2403.11671)]\r\n4. RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Models [2023-arxiv] [[paper](https://arxiv.org/pdf/2311.16543)]\r\n5. LLM4SecHW: Leveraging domain-specific large language model for hardware debugging [2023-AsianHOST] [[paper](https://arxiv.org/pdf/2401.16448)]\r\n\r\n### GUI Bug\r\n\r\n1. Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing [2025-ASE] [[repo](https://sites.google.com/view/guirepair)]\r\n2. SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains? [2025-ICLR] [[repo](https://swebench.com/multimodal)]\r\n3. DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models [2025-ICSE] [[repo](https://github.com/UGAIForge/DesignRepair)]\r\n\r\n### Performance Bug\r\n\r\n1. RAPGen: An Approach for Fixing Code Inefficiencies in Zero-Shot [2023-arxiv] [[paper](https://arxiv.org/pdf/2306.17077)]\r\n2. DeepDev-PERF: A Deep Learning-Based Approach for Improving Software Performance [2022-FSE/ESEC] [[paper](https://dl.acm.org/doi/abs/10.1145/3540250.3549096)] [[repo](https://github.com/glGarg/DeepDev-PERF)]\r\n\r\n### API Misuse\r\n\r\n1. Evaluating Pre-trained Language Models for Repairing API Misuses [2023-arxiv] [[paper](https://arxiv.org/pdf/2310.16390)] [[repo](https://anonymous.4open.science/r/TOSEM-API-Misuse)]\r\n\r\n### Formal Specification\r\n\r\n1. An Empirical Evaluation of Pre-trained Large Language Models for Repairing Declarative Formal Specifications [2024-EMSE] [[repo](https://github.com/Mohannadcse/AlloySpecRepair)]\r\n\r\n### Crash Bug\r\n\r\n1. Resolving Crash Bugs via Large Language Models: An Empirical Study [2023-arxiv] [[paper](https://arxiv.org/pdf/2312.10448)] [[repo](https://chatgpt4cradiag.github.io/)]\r\n\r\n### Test Case\r\n\r\n1. FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair [2024-TSE] [[repo](https://github.com/TestingResearchIllinois/idoft)]\r\n2. NIODebugger: A Novel Approach to Repair Non-Idempotent-Outcome Tests with LLM-Based Agent [2025-ICSE] [[repo](https://github.com/zhenlongDai/)]\r\n3. Automated Test Case Repair Using Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2401.06765)]\r\n4. Identify and Update Test Cases when Production Code Changes: A Transformer-based Approach [2023-ASE]\r\n\r\n### Error-handling Bug\r\n\r\n1. Error Delayed Is Not Error Handled: Understanding and Fixing Propagated Error-Handling Bugs [2025-FSE/ESEC] [[repo](https://github.com/EH-Fixer/EH-Fixer)]\r\n\r\n\r\n### Formal Proof\r\n\r\n1. Baldur: Whole-Proof Generation and Repair with Large Language Models [2023-FSE/ESEC] [[paper](https://arxiv.org/pdf/2303.04910)]\r\n\r\n### Translation Bug\r\n\r\n1. Lost in Translation: A Study of Bugs Introduced by Large Language Models while Translating Code [2024-ICSE] [[paper](https://dl.acm.org/doi/pdf/10.1145/3597503.3639226)] [[repo](https://github.com/Intelligent-CAT-Lab/PLTranslationEmpirical)]\r\n\r\n### GitHub Issue\r\n\r\n1. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? [2024-ICLR] [[paper](https://arxiv.org/pdf/2310.06770)] [[repo](https://github.com/princeton-nlp/SWE-bench)]\r\n\r\n### Code Review\r\n\r\n1. Divide-and-Conquer: Automating Code Revisions via Localization-and-Revision [2024-TOSEM] [[repo](https://zenodo.org/records/8373320)]\r\n2. Exploring the Potential of ChatGPT in Automated Code Refinement: An Empirical Study [2024-ICSE] [[paper](https://arxiv.org/pdf/2309.08221)] [[repo](https://sites.google.com/view/chatgptcodereview)]\r\n\r\n### Motion Planner\r\n\r\n1. DrPlanner: Diagnosis and Repair of Motion Planners Using Large Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2403.07470)] [[repo](https://github.com/CommonRoad/drplanner)]\r\n\r\n\r\n## 🙆 Human Study\r\n\r\n1. Exploring Experiences with Automated Program Repair in Practice [2024-ICSE] [[paper](https://dl.acm.org/doi/pdf/10.1145/3597503.3639182)]\r\n2. Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2404.15236)] [[repo](https://zenodo.org/records/10851256)]\r\n3. An Empirical Study of Adoption of ChatGPT for Bug Fixing among Professional Developers [2023-ITA] [[paper](https://bergersci.com/index.php/jta/article/download/19/20)]\r\n\r\n## 🙅 Patch Correctness Assessment\r\n\r\n1. 🔥Leveraging Large Language Model for Automatic Patch Correctness Assessment[2024-TSE] [[paper](https://ieeexplore.ieee.org/document/10659742)]\r\n2. APPT Boosting Automated Patch Correctness Prediction via Pre-trained Language Model [2024-TSE] [[paper](https://arxiv.org/pdf/2301.12453)] [[repo](https://github.com/iSEngLab/APPT)]\r\n3. The Best of Both Worlds: Combining Learned Embeddings with Engineered Features for Accurate Prediction of Correct Patches [2023-TOSME] [[paper](https://dl.acm.org/doi/pdf/10.1145/3576039)] [[repo](https://github.com/HaoyeTianCoder/Panther)]\r\n4. Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning [2023-TSE] [[paper](https://arxiv.org/pdf/2301.01113)] [[repo](https://github.com/thanhlecongg/Invalidator)]\r\n5. PatchZero: Zero-Shot Automatic Patch Correctness Assessment [2023-arxiv] [[paper](https://arxiv.org/pdf/2303.00202)]\r\n6. Is this Change the Answer to that Problem? Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctness [2021-ASE] [[paper](https://dl.acm.org/doi/pdf/10.1145/3551349.3556914)] [[repo](https://github.com/Trustworthy-Software/Quatrain)]\r\n7. Evaluating representation learning of code changes for predicting patch correctness in program repair [2020-ASE] [[paper](https://arxiv.org/pdf/2008.02944)] [[repo](https://github.com/TruX-DTF/DL4PatchCorrectness)]\r\n\r\n## 📊 Benchmark\r\n\r\n1. 🔥Exploring Parameter-Efficient Fine-Tuning of Large Language Model on Automated Program Repair[2024-ASE] [[paper](https://dl.acm.org/doi/abs/10.1145/3691620.3695066)]\r\n2. 🔥MuBench: Benchmarking Automated Program Repair: An Extensive Study on Both Real-World and Artificial Bugs [2024-ISSTA]  [[paper](https://dl.acm.org/doi/10.1145/3650212.3652140)]\r\n3. CodeEditorBench: Evaluating Code Editing Capability of Large Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2404.03543)] [[repo](https://github.com/CodeEditorBench/CodeEditorBench)]\r\n4. GitBug-Java: A Reproducible Benchmark of Recent Java Bugs [2024-arxiv] [[paper](https://arxiv.org/pdf/2402.02961)] [[repo](https://github.com/gitbugactions/gitbug-java)]\r\n5. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? [2024-ICLR] [[paper](https://arxiv.org/pdf/2310.06770)] [[repo](https://github.com/princeton-nlp/SWE-bench)]\r\n6. DebugBench: Evaluating Debugging Capability of Large Language Models [2024-arxiv] [[paper](https://arxiv.org/pdf/2401.04621)] [[repo](https://github.com/thunlp/DebugBench)]\r\n7. ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair [2024-arxiv] [[paper](https://arxiv.org/pdf/2310.16253)] [[repo](https://github.com/appmlk/ConDefects)]\r\n8. A critical review of large language model on software engineering: An example from chatgpt and automated program repair [2023-arxiv] [[paper](https://arxiv.org/pdf/2310.08879)] [[repo](https://github.com/iSEngLab/EvalGPTFix)]\r\n9. CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation [2023-arxiv] [[paper](https://arxiv.org/pdf/2311.08588)] [[repo](https://github.com/WeixiangYAN/CodeScope)]\r\n10. FixEval: Execution-based Evaluation of Program Fixes for Programming Problems [2023-APR] [[paper](https://arxiv.org/pdf/2206.07796)] [[repo](https://github.com/mahimanzum/FixEval)]\r\n\r\n## 🤔 Related APR Surveys\r\n\r\n1. A Survey of Learning-based Automated Program Repair [2023-TOSEM] [[paper](https://arxiv.org/abs/2301.03270)] [[repo](https://github.com/iSEngLab/AwesomeLearningAPR)]\r\n2. Automatic Software Repair: A Bibliography [2018-CSUR] [paper](https://dl.acm.org/doi/10.1145/3105906)]\r\n3. Automatic Software Repair: A Survey [2017-TSE] [paper](https://dl.acm.org/doi/10.1109/TSE.2017.2755013)]\r\n\r\n## Star History\r\n\r\n[![Star History Chart](https://api.star-history.com/svg?repos=iSEngLab/AwesomeLLM4APR\u0026type=Date)](https://star-history.com/#iSEngLab/AwesomeLLM4APR\u0026Date)\r\n\r\n\r\n\r\n\r\n\r\n\r\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/isenglab%2Fawesomellm4apr/projects"}