通过对话图谱自动发现大模型协作团队，无需了解模型内部结构。
The Geometry of Dialogue: Graphing Language Models to Reveal Synergistic Teams for Multi-Agent Collaboration
- 构建语言模型对话图，基于语义连贯性映射模型关系。
- 识别出功能一致的模型集群，性能接近人工精选团队。
- 适合想自动化组建大模型协作系统的研究人员。
多智能体大语言模型（LLM）协同虽具潜力，但成功依赖于协同团队的优化组合。然而，由于多数模型内部机制不透明，难以确定高效协作组合。本文提出一种无需先验知识（如架构、训练数据或任务表现）的交互中心框架。通过分析成对对话的语义连贯性，构建“语言模型图”，并运用社区检测算法识别出具有协同特性的模型集群。实验表明，该方法能发现反映模型潜在专长的功能一致性群体。在特定话题引导下，所发现的团队在下游基准测试中优于随机基线，并达到与基于已知专长的人工筛选团队相当的准确率。研究为自动化设计协作型多智能体大模型团队提供了新思路。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。