HyperAgent：利用超图实现多智能体通信中的拓扑优化

HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication

October 12, 2025

作者: Heng Zhang, Yuling Shi, Xiaodong Gu, Zijian Zhang, Haochen You, Lubin Gan, Yilei Yuan, Jin Huang

cs.AI

摘要

近期，基于大语言模型的多智能体系统通过高效通信展现了显著的集体智能。然而，现有方法面临两大主要挑战：(i) 群体协作建模效果不佳，因其依赖图结构中的成对边表示，限制了捕捉多智能体间关系的能力；(ii) 通信拓扑设计缺乏任务适应性，导致简单任务下通信成本过高，而复杂场景下协调不足。这些问题制约了自适应协作框架的可扩展性和实际部署。为解决这些挑战，我们提出了HyperAgent，一种基于超图的框架，通过直接超边表示优化通信拓扑并有效捕捉群体协作模式。与基于边的方法不同，HyperAgent使用超边将同一子任务中的多个智能体连接起来，并利用超图卷积层实现协作群体中的一步信息聚合。此外，它结合了带有稀疏正则化的变分自编码器框架，根据任务复杂度动态调整超图拓扑。实验结果表明，HyperAgent在性能和效率上均表现出色。例如，在GSM8K数据集上，HyperAgent达到了95.07%的准确率，同时减少了25.33%的令牌消耗，展示了基于超图优化的多智能体通信潜力。

English

Recent advances in large language model-powered multi-agent systems have demonstrated remarkable collective intelligence through effective communication. However, existing approaches face two primary challenges: (i) Ineffective group collaboration modeling, as they rely on pairwise edge representations in graph structures, limiting their ability to capture relationships among multiple agents; and (ii) Limited task-adaptiveness in communication topology design, leading to excessive communication cost for simple tasks and insufficient coordination for complex scenarios. These issues restrict the scalability and practical deployment of adaptive collaboration frameworks. To address these challenges, we propose HyperAgent, a hypergraph-based framework that optimizes communication topologies and effectively captures group collaboration patterns using direct hyperedge representations. Unlike edge-based approaches, HyperAgent uses hyperedges to link multiple agents within the same subtask and employs hypergraph convolutional layers to achieve one-step information aggregation in collaboration groups. Additionally, it incorporates a variational autoencoder framework with sparsity regularization to dynamically adjust hypergraph topologies based on task complexity. Experiments highlight the superiority of HyperAgent in both performance and efficiency. For instance, on GSM8K, HyperAgent achieves 95.07\% accuracy while reducing token consumption by 25.33\%, demonstrating the potential of hypergraph-based optimization for multi-agent communication.