EUVIMEDEUVIMED entdecken
Crossref

PReMM: LLM-Based Program Repair for Multi-method Bugs via Divide and Conquer

Linna Xie, Zhong Li, Yu Pei, Zhongzhen Wen, Kui Liu, Tian Zhang, Xuandong Li

Proceedings of the ACM on Programming Languages · 09.10.2025 · 9 (OOPSLA2) · 1316-1344

DOI: 10.1145/3763097 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Programming Languages, online erschienen am 09.10.2025. Verfasst von Linna Xie und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large-language models (LLMs) have been leveraged to enhance the capability of automated program repair techniques in recent research. While existing LLM-based program repair techniques compared favorably to other techniques based on heuristics, constraint-solving, and learning in producing high-quality patches, they mainly target bugs that can be corrected by changing a single faulty method, which greatly limits the effectiveness of such techniques in repairing bugs that demand patches spanning across multiple methods. In this work, we propose the PReMM technique to effectively propose patches changing multiple methods. PReMM builds on three core component techniques: the faulty method clustering technique to partition the faulty methods into clusters based on the dependence relationship among them, enabling a divide-and-conquer strategy for the repairing task; the fault context extraction technique to gather extra information about the fault context which can be utilized to better guide the diagnosis of the fault and the generation of correct patches; the dual-agent-based patch generation technique that employs two LLM-based agents with different roles to analyze the fault more precisely and generate patches of higher-quality. We have implemented the PReMM technique into a tool with the same name and applied the tool to repair real-world bugs from datasets Defects4J V1.2 and V2.0. PReMM produced correct patches for 307 bugs in total. Compared with ThinkRepair, the state-of-the-art LLM-based program repair technique, PReMM correctly repaired 102 more bugs, achieving an improvement of 49.8%.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangsu Province
  • China Postdoctoral Science Foundation
  • Postdoctoral Fellowship Program of CPSF
  • Hong Kong Polytechnic University Fund

Zitieren

APA

Xie, L., Li, Z., Pei, Y., Wen, Z., Liu, K., Zhang, T., & Li, X. (2025). PReMM: LLM-Based Program Repair for Multi-method Bugs via Divide and Conquer. Proceedings of the ACM on Programming Languages, 9(OOPSLA2), 1316-1344. https://doi.org/10.1145/3763097

Vancouver

Xie L, Li Z, Pei Y, Wen Z, Liu K, Zhang T, et al. PReMM: LLM-Based Program Repair for Multi-method Bugs via Divide and Conquer. Proceedings of the ACM on Programming Languages. 2025;9(OOPSLA2):1316-1344. doi:10.1145/3763097

BibTeX
@article{Xie2025,
  author = {Xie, Linna and Li, Zhong and Pei, Yu and Wen, Zhongzhen and Liu, Kui and Zhang, Tian and Li, Xuandong},
  title = {PReMM: LLM-Based Program Repair for Multi-method Bugs via Divide and Conquer},
  journal = {Proceedings of the ACM on Programming Languages},
  year = {2025},
  volume = {9},
  number = {OOPSLA2},
  pages = {1316--1344},
  doi = {10.1145/3763097}
}
Kostenlos starten →