PulseAugur
实时 07:28:27
English(EN) Autonomous Repair for Multi-Agent Systems via Monte-Carlo Tree Search

新的MARS框架实现了多智能体系统的自主修复

研究人员开发了MARS,一个用于自主修复多智能体系统(MAS)的新型基于搜索的框架。MARS将修复过程构建为蒙特卡洛树搜索(MCTS)问题,通过诊断引导的扩展和分类增强的评估来导航潜在解决方案。该方法在新提出的StateMAS基准测试中表现显著优于现有方法,该基准测试包含1,310个多智能体故障轨迹。MARS在有效管理令牌消耗的同时,显著提高了修复准确性。 AI

影响 增强了多智能体系统的鲁棒性和自主性,有可能减少复杂AI部署中的手动干预。

排序理由 该集群描述了一篇详细介绍多智能体系统新框架和基准测试的研究论文。

在 arXiv cs.MA (Multiagent) 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的MARS框架实现了多智能体系统的自主修复

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Hanxiao Lu, Tianyi Zhang ·

    基于蒙特卡洛树搜索的多智能体系统自主修复

    arXiv:2607.29055v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly deployed to solve complex tasks. In case of incorrect or unsatisfactory outputs, users have to manually locate agent mistakes by inspecting agent trajectories (i.e., {\em failure attribut…

  2. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Tianyi Zhang ·

    基于蒙特卡洛树搜索的多智能体系统自主修复

    Multi-agent systems (MAS) are increasingly deployed to solve complex tasks. In case of incorrect or unsatisfactory outputs, users have to manually locate agent mistakes by inspecting agent trajectories (i.e., {\em failure attribution}) and provide feedback to refine the outputs (…