MA-Mesh：基于角色自愈的多智能体弹性协作框架
MA-Mesh: Resilient Multi-Agent Collaboration via Role-based Self-Healing
AI 导读
研究者提出多智能体框架 MA-Mesh，在协作模式之上构建基于角色的自愈层，将弹性感知的系统规约合成为可执行的多智能体策略代码。框架引入跨智能体反思与基于角色的故障接管两项机制，让智能体互相评估并动态重分配角色以保障任务连续性。在软件开发、工具使用、科学推理等任务上，MA-Mesh 的任务性能与不确定性下的鲁棒性均显著优于现有多智能体系统，论文已被 EMNLP 2026 主会接收。
正文 · 原文
Abstract: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.
| Comments: | Accepted at EMNLP 2026 (Main) |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.06389 [cs.AI] |
| (or arXiv:2611.06389v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06389 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Junyong Lee [view email]
[v1]
Wed, 4 Nov 2026 11:54:59 UTC (2,079 KB)
来源：arXiv cs.AI · arxiv.org