MA-Mesh:基于角色的自修复实现弹性多智能体协作
MA-Mesh: Resilient Multi-Agent Collaboration via Role-based Self-Healing
AI总结:
本研究提出MA-Mesh框架,通过跨智能体反射和基于角色的故障转移两种自修复机制,提升多智能体系统在动态不确定环境下的协作弹性,实验显示其性能与鲁棒性均优于现有系统。
摘要:
多智能体系统中的有效协作需要在动态且不确定环境下的协调与适应机制。然而,现有多智能体系统很少明确建模弹性,而是依赖临时的输出修正,这限制了对鲁棒性的系统性运行时管理。本研究提出Multi-Agent Mesh(MA-Mesh)框架,它在协作模式之上构建基于角色的自修复层。具体而言,MA-Mesh生成感知弹性的系统规范,并将其合成为可执行的多智能体策略代码。为增强弹性,我们引入两种自修复机制:跨智能体反射,该机制允许智能体不仅评估自身结果,还评估同伴的性能,从而实现明智的行为调整和集体策略优化;基于角色的故障转移,该策略动态重新分配角色,当子任务失败或智能体表现不佳时,使智能体能够相互替代,确保任务执行的连续性。在软件开发、工具使用、科学推理等不同任务上的实验结果表明,MA-Mesh在系统不确定性下的任务性能和鲁棒性方面显著优于现有多智能体系统。
英文摘要:
Effective collaboration in multi-agent systems requires mechanisms for coordination and adaptability in dynamic and uncertain environments. However, existing multi-agent systems rarely model resilience explicitly, instead relying on ad-hoc output correction that limits systematic, runtime management of robustness. In this work, we propose Multi-Agent Mesh (MA-Mesh), a framework that constructs a role-based self-healing layer on top of a collaboration pattern. Specifically, MA-Mesh generates resilience-aware system specifications and synthesizes them into executable multi-agent policy code. To enhance resilience, we introduce two self-healing mechanisms: Cross-agent reflection, a mechanism that allows agents to evaluate not only their own outcomes but also the performance of their peers, enabling informed behavioral adjustments and collective policy refinement; Role-based failover, a strategy which dynamically reassigns roles and enables agents to substitute for one another when sub-tasks fail or agents underperform, ensuring continuity of task execution. Experimental results across diverse tasks (e.g., software development, tool use, scientific reasoning) demonstrate that MA-Mesh significantly outperforms existing multi-agent systems in both task performance and robustness under system uncertainty.
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。