Med-SRAF: A Multi-Agent Framework for Medical Reasoning via Semantic Routing and Agentic Fusion

While Retrieval-Augmented Generation (RAG) has become a standard paradigm for mitigating hallucinations in Large Language Models (LLMs), its effectiveness in complex medical reasoning remains limited. Existing RAG methods suffer from two main challenges: First, Semantic Drift: without explicit domain constraints, LLM-driven query decomposition often deviates from the original clinical intent, introducing substantial noise that degrades retrieval relevance. Second, Concatenation Fallacy: retrieved evidence from different semantic aspects is aggregated in a naive, unstructured manner, without modeling their inter-dependencies and potential conflicts, which ultimately undermines downstream reasoning. To address these challenges, we propose Med-SRAF, a multi-agent retrieval augmentation framework guided by medical domain knowledge. This framework reconstructs the traditional RAG process through two core mechanisms: (1) Intent-driven Semantic Routing, where a UMLS-based Nav-igationAgent dynamically maps queries to medical dimensions for strategic search space pruning; and (2) Evidence-based Agentic Fusion, where a FusionAgent resolves conflicts among dimension-specific evidence to build logically consistent reasoning chains. Extensive experiments on five widely used medical benchmarks show that Med-SRAF consistently outperforms existing general RAG baselines, achieving an average accuracy improvement of over 4.7%, highlighting its effectiveness in robust and interpretable medical reasoning. Our code is at https://anonymous. 4open.science/r/MultiAgent_RAG-F6DC.