让多智能体协作图直接由外部证据生成，解决知识与结构不匹配问题。
When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems
- 将外部证据融入自回归图生成，动态构建协作拓扑
- 在GPQA专家级数据集上准确率领先基线15.7%，耗能减半
- 适合需要精准知识验证的复杂任务场景
多智能体系统（MAS）正从静态流程转向动态生成协作拓扑。然而，现有方法主要依赖大语言模型的参数化知识，外部搜索或检索仅作为被动工具，而非协作结构的显式决定因素，导致结构与知识错配，在知识密集型任务中出现冗余交互或验证不足。本文提出K-GAT（知识引导的智能体拓扑生成器），一种神经符号框架，将协作拓扑设计建模为知识条件下的结构学习问题，直接将外部证据整合到自回归图生成中。在知识密集型基准上的大量实验表明，K-GAT具备高效性与有效性：特别是在专家级的GPQA数据集上，其准确率比LLM-辩论基线高出15.7%，且计算令牌消耗不到一半。
原文摘要 · Abstract (English)
Multi-Agent Systems (MAS) have recently moved from static workflows toward dynamically generated collaboration topologies. However, existing topology generation methods rely primarily on the parametric knowledge of large language models, with external search or retrieval used only as a reactive tool rather than an explicit determinant of collaboration structure. This leads to structure-knowledge misalignment, where systems exhibit redundant interactions or insufficient verification in knowledge-intensive tasks. We propose K-GAT (Knowledge-Guided Agent Topology Generator), a neuro-symbolic framework that formulates collaboration topology design as a knowledge-conditioned structure learning problem, integrating external evidence directly into autoregressive graph generation. Extensive experiments on knowledge-intensive benchmarks demonstrate K-GAT's efficiency and effectiveness: notably on the expert-level GPQA dataset, K-GAT outperforms the LLM-Debate baseline by a substantial margin of +15.7% in accuracy, while consuming less than half the computational tokens.
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。