Talk to Right Specialists: Routing and Planning in Multi-agent System for Question Answering
This addresses limitations in RAG-based agents for cross-domain queries, though it is incremental as it builds on existing multi-agent and RAG techniques.
The paper tackles the problem of cross-domain question answering by proposing RopMura, a multi-agent system with routing and planning mechanisms, which effectively handles single-hop and multi-hop queries to improve response accuracy.
Leveraging large language models (LLMs), an agent can utilize retrieval-augmented generation (RAG) techniques to integrate external knowledge and increase the reliability of its responses. Current RAG-based agents integrate single, domain-specific knowledge sources, limiting their ability and leading to hallucinated or inaccurate responses when addressing cross-domain queries. Integrating multiple knowledge bases into a unified RAG-based agent raises significant challenges, including increased retrieval overhead and data sovereignty when sensitive data is involved. In this work, we propose RopMura, a novel multi-agent system that addresses these limitations by incorporating highly efficient routing and planning mechanisms. RopMura features two key components: a router that intelligently selects the most relevant agents based on knowledge boundaries and a planner that decomposes complex multi-hop queries into manageable steps, allowing for coordinating cross-domain responses. Experimental results demonstrate that RopMura effectively handles both single-hop and multi-hop queries, with the routing mechanism enabling precise answers for single-hop queries and the combined routing and planning mechanisms achieving accurate, multi-step resolutions for complex queries.