SWE-Debate, a competitive multi-agent framework, enhances issue resolution in software engineering by promoting diverse reasoning and achieving better issue localization and fix planning.
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.