返回全部动态
多智能体搜索中的吸收态相变
原标题：Absorbing State Phase Transitions in Multi-Agent Search
AI 摘要
该论文研究基于大语言模型的多智能体搜索任务，将搜索任务分为针式、链式、层次式和可分解四类，并用吸收态相变理论推导出临界通信度，即每个智能体最少需要通信的邻居数，超过该值错误假设就不会失控扩散。作者在软件配置调试和物理机制发现等真实任务上评估前沿LLM多智能体系统，发现确定性规则智能体行为与理论一致，但LLM智能体常不按拓扑通信、出现个体择优和羊群行为，导致理论假设失效。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
Absorbing State Phase Transitions in Multi-Agent Search Abstract Nontrivial dynamics can emerge in large language model (LLM)-based multi-agent systems, and preliminary evidence exists that formalisms from statistical mechanics can be effective at modeling and predicting such behaviors. In parallel, designing multi-agent communication topology for optimal task-solving is an active research question. In this paper, we focus on predicting the success of multi-agent search tasks using the formalis
发布时间：2026-10-01 12:00
抓取时间：2026-10-01 12:42
来源机构：arXiv