返回全部动态
基于因果推断发现高效可解释的LLM多智能体通信拓扑
原标题：Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference
AI 摘要
arXiv 上发布了一篇关于基于大语言模型的多智能体系统通信拓扑的研究论文。论文提出 E2-Explainer 框架，通过因果推断识别通信拓扑中的关键子图，以解释协作成功的原因并剪除冗余边。实验表明，该框架能有效降低通信成本并保持任务性能。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference Abstract The performance of large language model (LLM)-based multi-agent systems (MAS) largely depends on effective communication topologies. Existing topology generation methods, however, typically learn communication topologies through black-box optimization driven solely by task-level rewards. While effective, such optimization provides little insight into why particular commu
发布时间：2026-08-14 12:00
抓取时间：2026-08-14 12:39
来源机构：arXiv