Recent advances in multi-agent systems have shown great potential for solving complex tasks. However, when multiple agents edit a shared codebase concurrently, their changes can silently conflict and inconsistent views lead to integration failures. Existing multi-agent systems address this through workspace isolation (e.g., one git worktree per agent), but this defers conflict resolution to a post-hoc merge step where recovery is expensive. In this paper, we propose STORM, i.e., STate-ORiented Management for multi-agent collaboration. Specifically, STORM manages agent states by mediating their interactions with the shared workspace, ensuring that each agent operates on a consistent view of the codebase and that conflicting edits are detected and resolved at write time. We evaluate STORM on Commit0 and PaperBench across multiple LLMs. STORM outperforms the git-worktree-based multi-agent baseline by +18.7 on Commit0-Lite and +1.4 on PaperBench, while achieving comparable or better cost efficiency. Combined with single-agent runs, STORM reaches highest scores of 87.6 and 78.2 on the two benchmarks respectively, suggesting that explicit state management is a more effective foundation for multi-agent collaboration than workspace isolation. STORM can also be plugged into any multi-agent system seamlessly.

翻译：近年来，多智能体系统在解决复杂任务方面展现出巨大潜力。然而，当多个智能体同时编辑共享代码库时，它们的修改可能无声冲突，不一致的视图导致集成失败。现有系统通过工作空间隔离（例如，每个智能体使用一个Git工作树）来解决这一冲突，但这种方法将冲突解决推迟到后续的合并步骤，此时恢复成本高昂。本文提出STORM，即面向状态的多智能体协作管理策略。具体而言，STORM通过中介智能体与共享工作空间的交互来管理智能体状态，确保每个智能体在代码库的一致视图上操作，并在写入时检测并解决冲突编辑。我们在Commit0和PaperBench基准上，使用多个大语言模型对STORM进行评估。结果表明，STORM在Commit0-Lite上比基于Git工作树的多智能体基线方法提升+18.7分，在PaperBench上提升+1.4分，同时实现相当或更优的成本效率。结合单智能体运行，STORM在这两个基准上分别达到87.6和78.2的最高分，表明显式状态管理比工作空间隔离能更有效地支撑多智能体协作。STORM还可无缝集成到任何多智能体系统中。