Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915596564692992 |
|---|---|
| author | Lumer, Elias Nizar, Faheem Gulati, Anmol Basavaraju, Pradeep Honaganahalli Subbiah, Vamse Kumar |
| author_facet | Lumer, Elias Nizar, Faheem Gulati, Anmol Basavaraju, Pradeep Honaganahalli Subbiah, Vamse Kumar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_01854 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems Lumer, Elias Nizar, Faheem Gulati, Anmol Basavaraju, Pradeep Honaganahalli Subbiah, Vamse Kumar Computation and Language 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. |
| title | Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2511.01854 |