Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts

ArXi:2604.00901v1 Announce Type: new Multi-agent Retrieval-Augmented Generation (RAG), wherein each agent takes on a specific role, s hard queries that require multiple steps and sources, or complex reasoning. Existing approaches, however, rely on static agent behaviors and fixed orchestration strategies, leading to brittle performance on diverse, multi-hop tasks. We identify two key limitations: the lack of continuously adaptive orchestration mechanisms and the absence of behavior-level learning for individual agents.