Lune

ACL Findings2025

SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution

Chengxing Xie, Bowen Li, Chang Gao, He Du, Wai Lam, Difan Zou, Kai Chen

Abstract

Large Language Models (LLMs) have demonstrated remarkable proficiency across a variety of complex tasks. One significant application of LLMs is in tackling software engineering challenges, particularly in resolving real-world tasks on GitHub by fixing code based on the issues reported by the users. However, many current approaches rely on proprietary LLMs, which limits reproducibility, accessibility, and transparency. The critical components of LLMs for addressing software engineering issues and how their capabilities can be effectively enhanced remain unclear. To address these challenges, we introduce SWE-Fixer, a novel opensource framework designed to effectively and efficiently resolve GitHub issues. SWE-Fixer comprises two essential modules: a code file retrieval module and a code editing module. The retrieval module employs BM25 along with a lightweight model to achieve coarse-to-fine file retrieval. Subsequently, the code editing module utilizes the other model to generate patches for the identified files. To mitigate the lack of publicly available datasets, we compile an extensive dataset that includes 110K GitHub issues along with their corresponding patches and train the two models of SWE-Fixer separately. We assess our approach on the SWE-Bench Lite and Verified benchmarks, achieving competitive performance among open-source models with scores of 22.0% and 30.2%. Furthermore, SWE-Fixer reaches state-of-the-art performance (24.7% on Lite and 32.8% on Verified) with PASS_TO_PASS (P2P) filtering. Additionally, our approach requires only two model calls per instance, making it significantly more efficient than existing methods. These results highlight the effectiveness of SWE-Fixer in real-world code-fixing scenarios. We will make our model, dataset, and code publicly available at https://github.com/InternLM/ SWE-Fixer.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

23 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Kimi-Dev: Agentless Training as Skill Prior for SWE-agents cites SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
  • Kimi-Dev: Agentless Training as Skill Prior for SWE-agents cites SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
  • SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution cites Impact of Code Language Models on Automated Program Repair
  • SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution cites SWE-bench: Can Language Models Resolve Real-world Github Issues?
  • SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution cites SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
  • SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution cites Automated Program Repair in the Era of Large Pre-trained Language Models
  • SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering cites SWE-bench: Can Language Models Resolve Real-world Github Issues?
  • Repo2Run: Automated Building Executable Environment for Code Repository at Scale cites SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
  • Repo2Run: Automated Building Executable Environment for Code Repository at Scale cites SWE-bench: Can Language Models Resolve Real-world Github Issues?
  • Repo2Run: Automated Building Executable Environment for Code Repository at Scale cites SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
  • Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks cites SWE-bench: Can Language Models Resolve Real-world Github Issues?
  • Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks cites SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
  • SWERank: Software Issue Localization with Code Ranking cites SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers23

  1. SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software EvolutionYuxiang Wei, Olivier Duchenne, Jade Copet, Quentin Carbonneaux et al.NeurIPS 2025 · 291 citations
  2. Repo2Run: Automated Building Executable Environment for Code Repository at ScaleRuida Hu, Chao Peng, Xinchen Wang, Junjielong Xu et al.NeurIPS 2025 · 49 citations
  3. Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering TasksHongyuan Tao, Ying Zhang, Zhenhao Tang, Hongen Peng et al.NeurIPS 2025 · 41 citations
  4. Kimi-Dev: Agentless Training as Skill Prior for SWE-agentsZonghan Yang, Shengjie Wang, Kelin Fu, Wenyang He et al.ICLR 2026 · 34 citations
  5. SWERank: Software Issue Localization with Code RankingRevanth Gangi Reddy, Tarun Suresh, JaeHyeok Doo, Ye Liu et al.ICLR 2026 · 28 citations

Builds on17

  1. SWE-bench: Can Language Models Resolve Real-world Github Issues?Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao et al.ICLR 2024 · 2,082 citations
  2. SWE-agent: Agent-Computer Interfaces Enable Automated Software EngineeringJohn Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret et al.NeurIPS 2024 · 2,059 citations
  3. STaR: Bootstrapping Reasoning With ReasoningEric Zelikman, Yuhuai Wu, Jesse Mu, Noah D. GoodmanNeurIPS 2022 · 1,126 citations
  4. Automated Program Repair in the Era of Large Pre-trained Language ModelsChunqiu Steven Xia, Yuxiang Wei, Lingming ZhangICSE 2023 · 321 citations
  5. Impact of Code Language Models on Automated Program RepairNan Jiang, Kevin Liu, Thibaud Lutellier, Lin TanICSE 2023 · 164 citations

Related papers

  1. SWE-GPT: A Process-Centric Language Model for Automated Software ImprovementYingwei Ma, Rongyu Cao, Yongchang Cao, Yue Zhang et al.ISSTA 2025 · 1 citation
  2. AutoCodeRover: Autonomous Program ImprovementYuntong Zhang, Haifeng Ruan, Zhiyu Fan, Abhik RoychoudhuryISSTA 2024 · 96 citations
  3. SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue ResolutionZhenyu He, Qingping Yang, Wei Shen, Xiaojian Zhong et al.ACL Findings 2026
  4. MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue ResolutionWei Tao, Yucheng Zhou, Yanlin Wang, Wenqiang Zhang et al.NeurIPS 2024 · 210 citations
  5. SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?Xinyi He, Qian Liu, Mingzhe Du, Lin Yan et al.ICML 2026 · 31 citations
Dusk over the sea between two cliffs drawn in fine vertical lines