一句话：提出竞争性多智能体辩论框架 SWE-Debate，通过故障传播轨迹与三轮辩论实现更统一的缺陷定位与补丁生成。
基于大语言模型的智能体在自动化软件问题修复上取得进展，但现有方法多依赖单个智能体的独立探索，容易陷入局部解，难以识别跨越代码库不同位置的问题模式。SWE-Debate 首先遍历代码依赖图，生成多条故障传播轨迹作为定位候选；随后组织三轮辩论，让持有不同推理视角的专门化智能体沿故障传播轨迹进行结构化竞争，从而协同收敛出统一的修复方案；最终该方案被送入基于 MCTS 的代码修改智能体以生成补丁。在 SWE-bench 基准上，SWE-Debate 在开源智能体框架中取得新的最优结果，并大幅优于基线。
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 margin1.
@inproceedings{abs-2507-23348,
title = {SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution},
author = {Han Li and Yuling Shi and Shaoxin Lin and Xiaodong Gu and Heng Lian and Xin Wang and Yantao Jia and Tao Huang and Qianxiang Wang},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3787810}
}