SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911084904972288 |
|---|---|
| author | Li, Han Shi, Yuling Lin, Shaoxin Gu, Xiaodong Lian, Heng Wang, Xin Jia, Yantao Huang, Tao Wang, Qianxiang |
| author_facet | Li, Han Shi, Yuling Lin, Shaoxin Gu, Xiaodong Lian, Heng Wang, Xin Jia, Yantao Huang, Tao Wang, Qianxiang |
| contents | Issue resolution has made remarkable progress thanks to the advanced reasoning capabilities of large language models (LLMs). Recently, agent-based frameworks such as SWE-agent have further advanced this progress by enabling autonomous, tool-using agents to tackle complex software engineering tasks. While existing agent-based issue resolution approaches are primarily based on agents' independent explorations, they often get stuck in local solutions and fail to identify issue patterns that span across different parts of the codebase. To address this limitation, we propose SWE-Debate, a competitive multi-agent debate framework that encourages diverse reasoning paths and achieves more consolidated issue localization. SWE-Debate first creates multiple fault propagation traces as localization proposals by traversing a code dependency graph. Then, it organizes a three-round debate among specialized agents, each embodying distinct reasoning perspectives along the fault propagation trace. This structured competition enables agents to collaboratively converge on a consolidated fix plan. Finally, this consolidated fix plan is integrated into an MCTS-based code modification agent for patch generation. Experiments on the SWE-bench benchmark show that SWE-Debate achieves new state-of-the-art results in open-source agent frameworks and outperforms baselines by a large margin. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23348 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution Li, Han Shi, Yuling Lin, Shaoxin Gu, Xiaodong Lian, Heng Wang, Xin Jia, Yantao Huang, Tao Wang, Qianxiang Software Engineering Computation and Language Machine Learning Issue resolution has made remarkable progress thanks to the advanced reasoning capabilities of large language models (LLMs). Recently, agent-based frameworks such as SWE-agent have further advanced this progress by enabling autonomous, tool-using agents to tackle complex software engineering tasks. While existing agent-based issue resolution approaches are primarily based on agents' independent explorations, they often get stuck in local solutions and fail to identify issue patterns that span across different parts of the codebase. To address this limitation, we propose SWE-Debate, a competitive multi-agent debate framework that encourages diverse reasoning paths and achieves more consolidated issue localization. SWE-Debate first creates multiple fault propagation traces as localization proposals by traversing a code dependency graph. Then, it organizes a three-round debate among specialized agents, each embodying distinct reasoning perspectives along the fault propagation trace. This structured competition enables agents to collaboratively converge on a consolidated fix plan. Finally, this consolidated fix plan is integrated into an MCTS-based code modification agent for patch generation. Experiments on the SWE-bench benchmark show that SWE-Debate achieves new state-of-the-art results in open-source agent frameworks and outperforms baselines by a large margin. |
| title | SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution |
| topic | Software Engineering Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2507.23348 |