多智能体搜索中的吸收态相变
Absorbing State Phase Transitions in Multi-Agent Search
查看机构详情
- University of California, Santa Barbara（加州大学圣巴巴拉分校）
- Flatiron Institute（熨斗研究院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本文利用吸收态相变理论预测多智能体搜索任务的成功，将搜索任务分为四类，推导临界通信度，并在真实任务上评估LLM多智能体系统，发现理论与实际表现存在差异。
中文摘要 AI 辅助
基于大语言模型（LLM）的多智能体系统中可以涌现出非平凡动力学，已有初步证据表明统计力学的形式化方法能够有效地建模和预测此类行为。与此同时，设计用于最优任务求解的多智能体通信拓扑是一个活跃的研究问题。在本文中，我们专注于使用吸收态相变的形式化方法来预测多智能体搜索任务的成功。我们首先根据组合搜索的经典结果，将搜索任务分类为四种类型。然后，我们从理论上推导出临界通信度 $d_c$，即每个智能体可以通信的最小智能体数量，高于该数量时，错误假设不会不受控制地扩散，搜索进入已求解状态。最后，我们在真实世界的搜索与发现任务（软件配置调试和物理机制发现）上评估前沿的基于LLM的多智能体系统，发现与理论的一致性参差不齐。LLM智能体可能不与邻居通信，并且可能发展出对个体有益但限制协作收益的策略。
英文摘要
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 formalism of absorbing state phase transitions. We first taxonomize search tasks into four types, informed by classical results in combinatorial search. We then theoretically derive a critical communication degree $d_c$, the minimum number of agents each agent can communicate with, above which incorrect hypotheses do not proliferate uncontrollably and the search enters the solved state. Finally, we evaluate frontier LLM-based multi-agent systems on real-world search and discovery tasks, software configuration debugging and physical mechanism discovery, and find that agreement with theory is mixed. LLM agents may not communicate with their neighbors and can develop strategies that are individually beneficial but limits the benefits of collaboration.
