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

ACL ARR 2026 January Submission4837 Authors

Keywords: RAG, Medical Reasoning, Multi-Agents, Semantic Routing, Agentic Fusion

Abstract: 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 NavigationAgent 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 **4.9\%**, highlighting its effectiveness in robust and interpretable medical reasoning.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: retrieval-augmented generation, pruning, clinical NLP, biomedical QA

Contribution Types: Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 4837