Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 2

The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.

SGAgent : Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repair

Zhang, Quanjun, Gao, Chengyu, Han, Yu, Shang, Ye, Fang, Chunrong, Chen, Zhenyu, Xiao, Liang·2026·ACM Transactions on Software Engineering and Methodology
DOI 10.1145/3818617
Open this paper in CoChat — free account

Abstract

The rapid advancement of Large Language Models (LLMs) has led to the emergence of intelligent agents capable of autonomously interacting with environments and invoking external tools. Recently, agent-based software repair approaches have received widespread attention, as repair agents can automatically analyze and localize bugs, generate patches, and achieve state-of-the-art performance on repository-level benchmarks (e.g., SWE-Bench). However, existing software repair approaches usually adopt a localize-then-fix paradigm , jumping directly from “where the bug is” to “how to fix it,” leaving a fundamental reasoning gap. To this end, we propose SGAgent , a S uggestion- G uided multi- Agent framework for repository-level software repair, which follows a localize-suggest-fix paradigm. Specifically, SGAgent introduces a suggestion to strengthen the transition from localization to repair. The suggester starts from the buggy locations and incrementally retrieves relevant context until it fully understands the bug, and then provides actionable repair suggestions. Moreover, we construct a Knowledge Graph (KG) from the target repository and develop a KG-based toolkit to enhance SGAgent ’s ability to enhance global contextual awareness and repository-level reasoning. Based on these components, three specialized sub-agents in SGAgent (i.e., localizer, suggester, and fixer) collaborate to achieve automated end-to-end software repair. We evaluated SGAgent on the SWE-Bench-Lite benchmark. Experimental results show that SGAgent with Claude-3.5 achieves 51.3% repair accuracy, 81.2% file-level, and 52.4% function-level localization accuracy with an average cost of $1.48 per instance, outperforming all baselines using the same base model. Moreover, SGAgent generalizes well across different base LLMs, further reaching a 60.7% resolution rate with Claude-4. When extended to vulnerability repair, SGAgent achieves a 48.0% resolution rate on VUL4J and VJBench, demonstrating strong generalization across tasks and programming languages.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3818617

Cites

8 of 8 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 8 references

Research works printed but not linked: 57

  1. Vaibhav Aggarwal Ojasv Kamal Abhinav Japesh Zhijing Jin and Bernhard Schölkopf. 2025. DARS: Dynamic action re-sampling to enhance coding agent performance by adaptive tree traversal. arXiv:2503.14269. Retrieved from https://arxiv.org/abs/2503.14269 · DOI
  2. Antonis Antoniades Albert Örwall Kexun Zhang Yuxi Xie Anirudh Goyal and William Wang. 2024. SWE-search: Enhancing software agents with Monte Carlo tree search and iterative refinement. arXiv:2410.20285. Retrieved from https://arxiv.org/abs/2410.20285 · arXiv
  3. Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le et al. 2021. Program synthesis with large language models. arXiv:2108.07732. Retrieved from https://arxiv.org/abs/2108.07732 · arXiv
  4. Islem Bouzenia Premkumar Devanbu and Michael Pradel. 2024. RepairAgent: An autonomous LLM-based agent for program repair. arXiv:2403.17134. Retrieved from https://arxiv.org/abs/2403.17134 · arXiv
  5. 10.1145/3524842.3528482 · DOI
  6. Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde De Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et al. 2021. Evaluating large language models trained on code. arXiv:2107.03374. Retrieved from https://arxiv.org/abs/2107.03374 · arXiv
  7. Zimin Chen Yue Pan Siyu Lu Jiayi Xu Claire Le Goues Martin Monperrus and He Ye. 2025. Prometheus: Unified knowledge graphs for issue resolution in multilingual codebases. arXiv:2507.19942. Retrieved from https://arxiv.org/abs/2507.19942 · arXiv
  8. DeepSeek-AI Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang et al. 2025. DeepSeek-V3 technical report. arXiv2412.19437. Retrieved from https://arxiv.org/abs/2412.19437 · arXiv
  9. Dawn Drain Colin B. Clement Guillermo Serrato and Neel Sundaresan. 2021. DeepDebug: Fixing python bugs using stack traces backtranslation and code skeletons. arXiv:2105.09352. Retrieved from https://arxiv.org/abs/2105.09352 · arXiv
  10. 10.1145/3597503.3639219 · DOI · Paper page
  11. 10.1145/3540250.3549098 · DOI · Paper page
  12. Michael Fu, Chakkrit Kla Tantithamthavorn, Van Nguyen, and Trung Le. 2023. ChatGpt for vulnerability detection, classification, and repair: How far are we? In Proceedings of the 2023 30th Asia-Pacific Software Engineering Conference (APSEC). IEEE, 632–636.
  13. 10.1109/ICSME58846.2023.00024 · DOI
  14. Xinyi Hou Yanjie Zhao Yue Liu Zhou Yang Kailong Wang Li Li Xiapu Luo David Lo John C. Grundy and Haoyu Wang. 2023. Large language models for software engineering: A systematic literature review. arXiv:2308.10620. Retrieved from https://arxiv.org/abs/2308.10620 · arXiv
  15. 10.1109/APR66717.2025.00007 · DOI
  16. Haichuan Hu Xiaochen Xie and Quanjun Zhang. 2025. Repair-r1: Better test before repair. arXiv:2507.22853. Retrieved from https://arxiv.org/abs/2507.22853 · arXiv
  17. Kai Huang, Jian Zhang, Xiangxin Meng, and Yang Liu. 2025. Template-guided program repair in the era of large language models. In Proceedings of the ICSE, 1895–1907.
  18. Juyong Jiang Fan Wang Jiasi Shen Sungju Kim and Sunghun Kim. 2024. A survey on large language models for code generation. arXiv:2406.00515. Retrieved from https://arxiv.org/abs/2406.00515 · arXiv
  19. 10.1109/ICSE48619.2023.00125 · DOI · Paper page
  20. 10.1109/ICSE43902.2021.00107 · DOI · Paper page
  21. Carlos E. Jimenez John Yang Alexander Wettig Shunyu Yao Kexin Pei Karthik Narasimhan and Ofir Press. 2023. SWE-bench: Can language models resolve real-world Github issues? arXiv:2310.06770. Retrieved from https://arxiv.org/abs/2310.06770 · arXiv
  22. 10.1145/3664646.3664770 · DOI · Paper page
  23. Dongcheng Li, W. Eric Wong, Mingyong Jian, Yi Geng, and Matthew Chau. 2022. Improving search-based automatic program repair with neural machine translation. IEEE Access 10 (2022), 51167–51175.
  24. Wei Liu Ailun Yu Daoguang Zan Bo Shen Wei Zhang Haiyan Zhao Zhi Jin and Qianxiang Wang. 2024. GraphCoder: Enhancing repository-level code completion via code context graph-based retrieval and language model. arXiv:2406.07003. Retrieved from https://arxiv.org/abs/2406.07003 · DOI
  25. Xiangyan Liu Bo Lan Zhiyuan Hu Yang Liu Zhicheng Zhang Fei Wang Michael Shieh and Wenmeng Zhou. 2024. CodexGraph: Bridging large language models and code repositories via code graph databases. arXiv:2408.03910. Retrieved from https://arxiv.org/abs/2408.03910 · arXiv
  26. Zijun Liu Yanzhe Zhang Peng Li Yang Liu and Diyi Yang. 2023. Dynamic LLM-agent network: An LLM-agent collaboration framework with agent team optimization. arXiv:2310.02170. Retrieved from https://arxiv.org/abs/2310.02170 · arXiv
  27. Elijah Mansur, Johnson Chen, Muhammad Anas Raza, and Mohammad Wardat. 2024. RAGFix: Enhancing LLM code repair using RAG and stack overflow posts. In Proceedings of the 2024 IEEE International Conference on Big Data (BigData). IEEE, 7491–7496.
  28. Justin J. Miller. 2013. Graph database applications and concepts with Neo4j. In Proceedings of the Southern Association for Information Systems Conference, Vol. 2324, 141–147.
  29. Fangwen Mu Junjie Wang Lin Shi Song Wang Shoubin Li and Qing Wang. 2025. EXPEREPAIR: Dual-memory enhanced LLM-based repository-level program repair. arXiv:2506.10484. Retrieved from https://arxiv.org/abs/2506.10484 · arXiv
  30. Siru Ouyang Wenhao Yu Kaixin Ma Zilin Xiao Zhihan Zhang Mengzhao Jia Jiawei Han Hongming Zhang and Dong Yu. 2024. RepoGraph: Enhancing AI software engineering with repository-level code graph. arXiv:2410.14684. Retrieved from https://arxiv.org/abs/2410.14684 · arXiv
  31. Shuyin Ouyang Jie M. Zhang Zeyu Sun and Albert Merono Penuela. 2025. Knowledge-enhanced program repair for data science code. arXiv:2502.09771. Retrieved from https://arxiv.org/abs/2502.09771 · arXiv
  32. Archit Parnami and Minwoo Lee. 2022. Learning from few examples: A summary of approaches to few-shot learning. arXiv:2203.04291. Retrieved from https://arxiv.org/abs/2203.04291 · arXiv
  33. 10.1109/SP46215.2023.10179324 · DOI
  34. Farhad Pourpanah, Moloud Abdar, Yuxuan Luo, Xinlei Zhou, Ran Wang, Chee Peng Lim, Xi-Zhao Wang, and Q. M. Jonathan Wu. 2022. A review of generalized zero-shot learning methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 4 (2022), 4051–4070.
  35. Samuel Schmidgall Yusheng Su Ze Wang Ximeng Sun Jialian Wu Xiaodong Yu Jiang Liu Michael Moor Zicheng Liu and Emad Barsoum. 2025. Agent laboratory: Using LLM agents as research assistants. arXiv:2501.04227. Retrieved from https://arxiv.org/abs/2501.04227 · DOI · Paper page
  36. Ye Shang, Quanjun Zhang, Chunrong Fang, Siqi Gu, Jianyi Zhou, and Zhenyu Chen. 2025. A large-scale empirical study on fine-tuning large language models for unit testing. Proceedings of the ACM on Software Engineering 2, ISSTA (2025), 1678–1700.
  37. 10.1109/TSE.2025.3581062 · DOI
  38. Yashar Talebirad and Amirhossein Nadiri. 2023. Multi-agent collaboration: Harnessing the power of intelligent LLM agents. arXiv:2306.03314. Retrieved from https://arxiv.org/abs/2306.03314 · arXiv
  39. 10.1145/3183519.3183540 · DOI
  40. 10.5555/3692070.3694124 · doi:10.5555/3692070.3694124
  41. Xingyao Wang Boxuan Li Yufan Song Frank F. Xu Xiangru Tang Mingchen Zhuge Jiayi Pan Yueqi Song Bowen Li Jaskirat Singh et al. 2024. OpenHands: An open platform for AI software developers as generalist agents. arXiv:2407.16741. Retrieved from https://arxiv.org/abs/2407.16741 · arXiv
  42. 10.1145/3386252 · DOI · Paper page
  43. Yuxiang Wei Olivier Duchenne Jade Copet Quentin Carbonneaux Lingming Zhang Daniel Fried Gabriel Synnaeve Rishabh Singh and Sida I. Wang. 2025. SWE-RL: Advancing LLM reasoning via reinforcement learning on open software evolution. arXiv:2502.18449. Retrieved from https://arxiv.org/abs/2502.18449 · arXiv
  44. 10.1145/3597926.3598135 · DOI
  45. Chunqiu Steven Xia Yinlin Deng Soren Dunn and Lingming Zhang. 2024. Agentless: Demystifying LLM-based software engineering agents. arXiv:2407.01489. Retrieved from https://arxiv.org/abs/2407.01489 · arXiv
  46. 10.1109/ICSE48619.2023.00129 · DOI · Paper page
  47. An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv:2505.09388. Retrieved from https://arxiv.org/abs/2505.09388 · arXiv
  48. Boyang Yang Haoye Tian Jiadong Ren Shunfu Jin Yang Liu Feng Liu and Bach Le. 2025. Enhancing repository-level software repair via repository-aware knowledge graphs. arXiv:2503.21710. Retrieved from https://arxiv.org/abs/2503.21710 · arXiv
  49. 10.52202/079017-1601 · DOI · Paper page
  50. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R. Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. In Proceedings of the 11th International Conference on Learning Representations.
  51. 10.1145/3533767.3534219 · DOI
  52. Quanjun Zhang Chunrong Fang Siqi Gu Ye Shang Zhenyu Chen and Liang Xiao. 2025. Large language models for unit testing: A systematic literature review. arXiv:2506.15227. Retrieved from https://arxiv.org/abs/2506.15227 · arXiv
  53. Quanjun Zhang, Chunrong Fang, Yuxiang Ma, Weisong Sun, and Zhenyu Chen. 2023. A survey of learning-based automated program repair. ACM Transactions on Software Engineering and Methodology 33, 2 (2023), 1–69. · DOI
  54. Quanjun Zhang Chunrong Fang Yang Xie Yuxiang Ma Weisong Sun Yun Yang and Zhenyu Chen. 2024. A systematic literature review on large language models for automated program repair. arXiv:2405.01466. Retrieved from https://arxiv.org/abs/2405.01466 · arXiv
  55. Quanjun Zhang Chunrong Fang Yang Xie Yaxin Zhang Yun Yang Weisong Sun Shengcheng Yu and Zhenyu Chen. 2026. A survey on large language models for software engineering. Science China Information Sciences 69 4 (2026) 141102. · DOI · Paper page
  56. 10.1109/ASE56229.2023.00063 · DOI
  57. Zibin Zheng Kaiwen Ning Yanlin Wang Jingwen Zhang Dewu Zheng Mingxi Ye and Jiachi Chen. 2023. A survey of large language models for code: Evolution benchmarking and future trends. arXiv:2311.10372. Retrieved from https://arxiv.org/abs/2311.10372 · arXiv

Metadata

Authors
Zhang, Q., Gao, C., Han, Y., Shang, Y., Fang, C., Chen, Z., & Xiao, L.
Venue
ACM Transactions on Software Engineering and Methodology
Publisher
Association for Computing Machinery (ACM)
Published
2026-11-04
Volume
35
Issue
11
Pages
1-33
ISSN
  • 1049-331X
  • 1557-7392
DOI
10.1145/3818617
Cited by
2
References
8
Language
en
Licence
creativecommons.org/licenses/by/4.0/legalcode (vor)
Funders
  • Natural Science Foundation of Jiangsu Province (BK20251458)
  • National Natural Science Foundation of China (U24A20337, 62372228)
  • Frontier Technologies R&D Program of Jiangsu (BF2024070)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: SGAgent : Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repair. https://app.cochat.ai/papers/10.1145/3818617
The paper
Zhang, Q., Gao, C., Han, Y., Shang, Y., Fang, C., Chen, Z., & Xiao, L. (2026). SGAgent : Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repair. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3818617

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.