让大模型代理系统精准找到匹配工具，提升任务执行效率。
Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems
- 将工具与代理统一嵌入向量空间，通过元数据关联实现细粒度检索。
- 在LiveMCPBench上召回率提升19.4%，nDCG提升17.7%。
- 适合需要高精度工具匹配的复杂多智能体系统研发者。
近期大模型多智能体系统实现了对数百甚至上千个工具或Model Context Protocol（MCP）服务器的可扩展编排。然而，现有检索方法通常仅基于粗粒度的代理描述进行查询匹配，掩盖了细粒度工具功能，常导致次优代理选择。我们提出Tool-to-Agent Retrieval，一个统一框架，将工具及其父代理嵌入共享向量空间，并通过元数据关系连接。通过显式表示工具能力并沿元数据路径追溯至代理层，该方法支持细粒度工具级或代理级检索，确保代理及其底层工具或MCP服务器均被平等表示，避免因合并大量工具而导致的上下文稀释问题。在八个嵌入模型上评估，本方法在LiveMCPBench基准上相较先前最先进代理检索器，召回率提升19.4%（Recall@5），nDCG提升17.7%（nDCG@5）。
原文摘要 · Abstract (English)
Recent advances in LLM Multi-Agent Systems enable scalable orchestration of sub-agents, each coordinating hundreds or thousands of tools or Model Context Protocol (MCP) servers. However, existing retrieval methods typically match queries against coarse agent-level descriptions before routing, which obscures fine-grained tool functionality and often results in suboptimal agent selection. We introduce Tool-to-Agent Retrieval, a unified framework that embeds both tools and their parent agents in a shared vector space and connects them through metadata relationships. By explicitly representing tool capabilities and traversing metadata to the agent level, Tool-to-Agent Retrieval enables granular tool-level or agent-level retrieval, ensuring that agents and their underlying tools or MCP servers are equally represented without the context dilution that arises from chunking many tools together. Evaluating Tool-to-Agent Retrieval across eight embedding models, our approach achieves consistent improvements of 19.4% in Recall@5 and 17.7% in nDCG@5 over previous state-of-the-art agent retrievers on the LiveMCPBench benchmark.
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。