While a multi-agent approach based on large language models (LLMs) represents a promising strategy to surpass the capabilities of single models, its success is critically dependent on synergistic team composition. However, forming optimal teams is a significant challenge, as the inherent opacity of most models obscures the internal characteristics necessary for effective collaboration. In this paper, we propose an interaction-centric framework for automatic team composition that does not require any prior knowledge including their internal architectures, training data, or task performances. Our method constructs a "language model graph" that maps relationships between models from the semantic coherence of pairwise conversations, and then applies community detection to identify synergistic model clusters. Our experiments with diverse LLMs demonstrate that the proposed method discovers functionally coherent groups that reflect their latent specializations. Priming conversations with specific topics identified synergistic teams which outperform random baselines on downstream benchmarks and achieve comparable accuracy to that of manually-curated teams based on known model specializations. Our findings provide a new basis for the automated design of collaborative multi-agent LLM teams.

翻译：基于大语言模型（LLMs）的多智能体方法虽有望超越单一模型的能力，但其成功关键取决于协同团队的构成。然而，多数模型的内在黑箱特性使得有效协作所需的内在特征难以获取，形成最优团队成为重大挑战。本文提出一种无需任何先验知识（包括模型内部架构、训练数据或任务性能）的交互中心化自动团队组建框架。该方法通过配对对话的语义连贯性构建"语言模型图谱"以映射模型间关系，进而应用社区检测识别协同模型集群。实验表明，该方法在多种LLM中发现了反映潜在专业化的功能同质化集群。通过特定主题引导对话可识别出协同团队，这些团队在下游基准测试中表现优于随机基线，且与基于已知模型专业化手工构建的团队相比，准确率相当。本研究为自动化设计协作式多智能体LLM团队提供了新基础。