Agent-as-a-Graph: Knowledge Graph-Based Tool and Agent Retrieval for LLM Multi-Agent Systems
This addresses inefficiencies in tool and agent retrieval for multi-agent systems, offering a domain-specific improvement.
The paper tackles the problem of suboptimal agent selection in Large Language Model Multi-Agent Systems by introducing Agent-as-a-Graph retrieval, a knowledge graph-based approach that improves Recall@5 and nDCG@5 by 14.9% and 14.6% over prior state-of-the-art methods.
Recent advances in Large Language Model Multi-Agent Systems enable scalable orchestration and retrieval of specialized, parallelized subagents, each equipped with hundreds or thousands of Model Context Protocol (MCP) servers and tools. However, existing agent, MCP, and retrieval methods typically match queries against a single agent description, obscuring fine-grained tool capabilities of each agent, resulting in suboptimal agent selection. We introduce Agent-as-a-Graph retrieval, a knowledge graph retrieval augmented generation approach that represents both tools and their parent agents as nodes and edges in a knowledge graph. During retrieval, i) relevant agents and tool nodes are first retrieved through vector search, ii) we apply a type-specific weighted reciprocal rank fusion (wRRF) for reranking tools and agents, and iii) parent agents are traversed in the knowledge graph for the final set of agents. We evaluate Agent-as-a-Graph on the LiveMCPBenchmark, achieving 14.9% and 14.6% improvements in Recall@5 and nDCG@5 over prior state-of-the-art retrievers, and 2.4% improvements in wRRF optimizations.