arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.30429cs.AI
收藏

RoleFlow:通过结构自适应实现自演化多角色智能体协作

RoleFlow: Self-Evolving Multi-Role Agentic Collaboration via Structural Adaptation

University of Maryland, College Park(马里兰大学帕克分校);University of Pittsburgh(匹兹堡大学);The University of Texas at Dallas(德克萨斯大学达拉斯分校)

Yi Ge, Pan Wang, Xuehao Cui, Zian Zeng, Xu Hu, Heng Huang, Furong Huang

AI总结:

该研究针对基于LLM的多智能体系统协作结构适应性不足的问题,提出RoleFlow系统,通过SECPO方法优化结构,在七个基准测试中性能最优,且具备多方面优势。

摘要:

基于大语言模型(LLM)的多智能体系统通常依赖预定义的协作结构,限制了其对不断变化的任务需求的适应性。尽管近期方法支持动态编排,但它们应用的轨迹级奖励为每个决策分配一个结果,往往难以识别单个结构变化的贡献。我们提出RoleFlow,一种自演化多角色智能体系统,它通过反馈驱动的原子编辑和按需角色合成来优化协作结构。为使结构自适应可学习,我们引入单编辑反事实策略优化(SECPO),该方法在相同链状态下将每个编辑与其无编辑对应项进行评估,并为编辑特定的标记分配针对性的 credit。在跨越四个领域的七个基准测试中,RoleFlow 取得了最优的平均性能,比最强的竞争对手高出 4.7 个点。它在所有三个多跳 QA 基准测试中领先 3.2-7.5 F1 点,在数学推理、网络交互和代码生成方面也表现出优势。进一步分析表明其具有跨基准可迁移性、训练数据效率和跨执行器泛化能力。

英文摘要:

Large language model (LLM) based multi-agent systems often rely on predefined collaboration structures, limiting their adaptability to evolving task requirements. Although recent approaches enable dynamic orchestration, trajectory-level rewards they apply assign one outcome to each decision, ofen struggling to identify the contributions of individual structural changes. We propose RoleFlow, a self-evolving multi-role agentic system that refines collaboration structures through feedback-driven atomic edits and on-demand role synthesis. To make structural adaptation learnable, we introduce Single-Edit Counterfactual Policy Optimization (SECPO), which evaluates each edit against its no-edit counterpart at the same chain state and assigns targeted credit to edit-specific tokens. Across seven benchmarks spanning four domains, RoleFlow achieves the optimal average performance, surpassing the strongest competitor by 4.7 points. It leads on all three multi-hop QA benchmarks by 3.2-7.5 F1 points and also shows supremacy on mathematical reasoning, web interaction, and code generation. Further analyses demonstrate cross-benchmark transferability, training-data efficiency, and cross-executor generalization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑