揭示大模型多智能体通信拓扑对信息传播的影响，提出高效鲁棒的拓扑设计方法。
Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems
- 构建因果框架分析不同稀疏度拓扑下的信息传播机制
- 中等稀疏拓扑在抑制错误传播与保留有效信息间取得平衡，性能最优
- 提出EIB-leanrner方法，融合密集与稀疏图优势，兼顾效率与鲁棒性
大型语言模型驱动的多智能体系统中，通信拓扑从根本上决定了智能体间的协作模式，显著影响集体决策的效率与效果。尽管现有研究倾向于设计稀疏拓扑以提升效率，却常忽视稀疏与密集拓扑在何种情境下促进或阻碍协作。本文提出一种因果分析框架，探究在不同稀疏度拓扑下，智能体输出（无论正确或错误）如何传播。实证研究表明，中等稀疏拓扑能有效抑制错误传播，同时保留有益信息扩散，通常实现最优任务性能。基于此洞察，我们提出新型拓扑设计方法EIB-leanrner，通过融合密集与稀疏图的连通模式，在误差抑制与有益信息传播间取得平衡。大量实验验证了EIB-leanrner在任务性能、通信成本和鲁棒性上的优越表现。
原文摘要 · Abstract (English)
The communication topology in large language model-based multi-agent systems fundamentally governs inter-agent collaboration patterns, critically shaping both the efficiency and effectiveness of collective decision-making. While recent studies for communication topology automated design tend to construct sparse structures for efficiency, they often overlook why and when sparse and dense topologies help or hinder collaboration. In this paper, we present a causal framework to analyze how agent outputs, whether correct or erroneous, propagate under topologies with varying sparsity. Our empirical studies reveal that moderately sparse topologies, which effectively suppress error propagation while preserving beneficial information diffusion, typically achieve optimal task performance. Guided by this insight, we propose a novel topology design approach, EIB-leanrner, that balances error suppression and beneficial information propagation by fusing connectivity patterns from both dense and sparse graphs. Extensive experiments show the superior effectiveness, communication cost, and robustness of EIB-leanrner.
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。