@inproceedings{li-etal-2026-med,
    title = "{M}ed-{SRAF}: A Multi-Agent Framework for Medical Reasoning via Semantic Routing and Agentic Fusion",
    author = "Li, Xiao  and
      Chen, Zhuo  and
      Xia, Jun  and
      Xiang, Hongxin  and
      Wang, Chao  and
      Du, Wenjie  and
      Wang, Yang",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1895/",
    pages = "38009--38029",
    ISBN = "979-8-89176-395-1",
    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. Our code is at https://anonymous.4open.science/r/MultiAgent{\_}RAG-F6DC."
}