MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning
This paper introduces MedRouter, an agentic system that uses an embedding-based multi-label router to select and query specialist LLMs, then passes their responses to a generator to produce the final answer, and proposes SCALE (Specialist Competence-Aware Learning), a two-stage training framework.
Lang Cao, Bing-Hang Lu, Yu-Hao Shen et al.
· 0 citations