AI RESEARCH

EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering

arXiv CS.CL

ArXi:2604.05149v1 Announce Type: new Large language model agents often exhibit complementary strengths, making routing a promising approach for multi-agent question answering. However, existing routing methods remain limited in two important ways: they typically optimize over a fixed pool of agents without improving the agents themselves, and they often rely on rigid collaboration schemes that cannot adapt the number of participating agents to the query.