UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging

Cheryl Lee, Chunqiu Steven Xia, Longji Yang, Jen-tse Huang, Zhouruixing Zhu, Lingming Zhang, Michael R. Lyu


Abstract
Software debugging is a time-consuming endeavor involving a series of steps, such as fault localization and patch generation, each requiring thorough analysis and a deep understanding of the underlying logic. While large language models (LLMs) demonstrate promising potential in coding tasks, their performance in debugging remains limited. Current LLM-based methods often focus on isolated steps and struggle with complex bugs. In this paper, we propose the first end-to-end framework, UniDebugger, for unified debugging through multi-agent synergy. It mimics the entire cognitive processes of developers, with each agent specialized as a particular component of this process rather than mirroring the actions of an independent expert as in previous multi-agent systems. Agents are coordinated through a three-level design, following a cognitive model of debugging, allowing adaptive handling of bugs with varying complexities. Experiments on extensive benchmarks demonstrate that UniDebugger significantly outperforms state-of-the-art repair methods, fixing 1.25x to 2.56x bugs on the repo-level benchmark, Defects4J. This performance is achieved without requiring ground-truth root-cause code statements, unlike the baselines. Our source code is available on an anonymous link: https://github.com/BEbillionaireUSD/UniDebugger.
Anthology ID:
2025.emnlp-main.921
Volume:
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18248–18277
Language:
URL:
https://aclanthology.org/2025.emnlp-main.921/
DOI:
Bibkey:
Cite (ACL):
Cheryl Lee, Chunqiu Steven Xia, Longji Yang, Jen-tse Huang, Zhouruixing Zhu, Lingming Zhang, and Michael R. Lyu. 2025. UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 18248–18277, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging (Lee et al., EMNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.emnlp-main.921.pdf
Checklist:
 2025.emnlp-main.921.checklist.pdf