@inproceedings{huang-etal-2026-sema,
title = "{SEMA}-{RAG}: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning",
author = "Huang, Yongfeng and
Chen, Ruiying and
Cheng, James",
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://aclanthology.org/2026.findings-acl.917/",
doi = "10.18653/v1/2026.findings-acl.917",
pages = "18423--18442",
ISBN = "979-8-89176-395-1",
abstract = "Retrieval-Augmented Generation (RAG) is widely employed to mitigate risks such as hallucinations and knowledge obsolescence in medical question answering, yet its predominantly single-round, static retrieval paradigm misaligns with the multi-stage process of clinical reasoning. This compressed workflow induces two structural deficiencies: question-to-query translation often lacks clinically grounded semantic interpretation, and retrieval lacks iterative sufficiency feedback, making it difficult to form reliable evidence chains. We argue that both issues stem from a deeper cause{---}overloading a single reasoning chain with heterogeneous tasks of interpretation, exploration, and adjudication{---}and that the remedy is to reconstruct the workflow via task decoupling and dynamic multi-round exploration. To this end, we propose the Self-Evolving Multi-Agent framework **SEMA-RAG**, which assigns these roles to three specialist agents: **Interpreter Agent** for clinical schema interpretation, **Explorer Agent** for sufficiency-driven self-evolving retrieval, and **Arbiter Agent** for evidence adjudication and answer selection. Across five benchmarks and five LLM backbones, SEMA-RAG improves the strongest baseline by **+6.46** accuracy points on average, measured per backbone."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-sema">
<titleInfo>
<title>SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yongfeng</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiying</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Retrieval-Augmented Generation (RAG) is widely employed to mitigate risks such as hallucinations and knowledge obsolescence in medical question answering, yet its predominantly single-round, static retrieval paradigm misaligns with the multi-stage process of clinical reasoning. This compressed workflow induces two structural deficiencies: question-to-query translation often lacks clinically grounded semantic interpretation, and retrieval lacks iterative sufficiency feedback, making it difficult to form reliable evidence chains. We argue that both issues stem from a deeper cause—overloading a single reasoning chain with heterogeneous tasks of interpretation, exploration, and adjudication—and that the remedy is to reconstruct the workflow via task decoupling and dynamic multi-round exploration. To this end, we propose the Self-Evolving Multi-Agent framework **SEMA-RAG**, which assigns these roles to three specialist agents: **Interpreter Agent** for clinical schema interpretation, **Explorer Agent** for sufficiency-driven self-evolving retrieval, and **Arbiter Agent** for evidence adjudication and answer selection. Across five benchmarks and five LLM backbones, SEMA-RAG improves the strongest baseline by **+6.46** accuracy points on average, measured per backbone.</abstract>
<identifier type="citekey">huang-etal-2026-sema</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.917</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.917/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>18423</start>
<end>18442</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning
%A Huang, Yongfeng
%A Chen, Ruiying
%A Cheng, James
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F huang-etal-2026-sema
%X Retrieval-Augmented Generation (RAG) is widely employed to mitigate risks such as hallucinations and knowledge obsolescence in medical question answering, yet its predominantly single-round, static retrieval paradigm misaligns with the multi-stage process of clinical reasoning. This compressed workflow induces two structural deficiencies: question-to-query translation often lacks clinically grounded semantic interpretation, and retrieval lacks iterative sufficiency feedback, making it difficult to form reliable evidence chains. We argue that both issues stem from a deeper cause—overloading a single reasoning chain with heterogeneous tasks of interpretation, exploration, and adjudication—and that the remedy is to reconstruct the workflow via task decoupling and dynamic multi-round exploration. To this end, we propose the Self-Evolving Multi-Agent framework **SEMA-RAG**, which assigns these roles to three specialist agents: **Interpreter Agent** for clinical schema interpretation, **Explorer Agent** for sufficiency-driven self-evolving retrieval, and **Arbiter Agent** for evidence adjudication and answer selection. Across five benchmarks and five LLM backbones, SEMA-RAG improves the strongest baseline by **+6.46** accuracy points on average, measured per backbone.
%R 10.18653/v1/2026.findings-acl.917
%U https://aclanthology.org/2026.findings-acl.917/
%U https://doi.org/10.18653/v1/2026.findings-acl.917
%P 18423-18442
Markdown (Informal)
[SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning](https://aclanthology.org/2026.findings-acl.917/) (Huang et al., Findings 2026)
ACL