cs.AINov 4, 2026

MA-Mesh: Resilient Multi-Agent Collaboration via Role-based Self-Healing

Authors: JunYong Lee, Woo Kyung Kim, Honguk Woo

Organizations: Department of Computer Science and Engineering, Sungkyunkwan University

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.

Figures & tables

Appendix figures & tables21 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. ResonAct: Streaming Metrics for Runtime Diagnosis and Self-Healing in Multi-Agent Systems

    Sep 28, 2026Tarun Chintada, Neelamadhav Gantayat, Ishaan Romil +3Agent Failure AnalysisAI Agent Monitoring

  2. BRIDGE: Selective Boundary Repair with Dependency Graph Evidence in Multi-Agent Systems

    Oct 13, 2026Encheng Su, Pengze Li, Ziheng Hua +12Multi-Agent CoordinationMulti-Agent Collaboration