Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Dong, Xuanzhao, Zhu, Wenhui, Wang, Hao, Chen, Xiwen, Qiu, Peijie, Yin, Rui, Su, Yi, Wang, Yalin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908343782604800
author Dong, Xuanzhao
Zhu, Wenhui
Wang, Hao
Chen, Xiwen
Qiu, Peijie
Yin, Rui
Su, Yi
Wang, Yalin
author_facet Dong, Xuanzhao
Zhu, Wenhui
Wang, Hao
Chen, Xiwen
Qiu, Peijie
Yin, Rui
Su, Yi
Wang, Yalin
contents Medical question answering (QA) is a reasoning-intensive task that remains challenging for large language models (LLMs) due to hallucinations and outdated domain knowledge. Retrieval-Augmented Generation (RAG) provides a promising post-training solution by leveraging external knowledge. However, existing medical RAG systems suffer from two key limitations: (1) a lack of modeling for human-like reasoning behaviors during information retrieval, and (2) reliance on suboptimal medical corpora, which often results in the retrieval of irrelevant or noisy snippets. To overcome these challenges, we propose Discuss-RAG, a plug-and-play module designed to enhance the medical QA RAG system through collaborative agent-based reasoning. Our method introduces a summarizer agent that orchestrates a team of medical experts to emulate multi-turn brainstorming, thereby improving the relevance of retrieved content. Additionally, a decision-making agent evaluates the retrieved snippets before their final integration. Experimental results on four benchmark medical QA datasets show that Discuss-RAG consistently outperforms MedRAG, especially significantly improving answer accuracy by up to 16.67% on BioASQ and 12.20% on PubMedQA. The code is available at: https://github.com/LLM-VLM-GSL/Discuss-RAG.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21252
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
Dong, Xuanzhao
Zhu, Wenhui
Wang, Hao
Chen, Xiwen
Qiu, Peijie
Yin, Rui
Su, Yi
Wang, Yalin
Computation and Language
Medical question answering (QA) is a reasoning-intensive task that remains challenging for large language models (LLMs) due to hallucinations and outdated domain knowledge. Retrieval-Augmented Generation (RAG) provides a promising post-training solution by leveraging external knowledge. However, existing medical RAG systems suffer from two key limitations: (1) a lack of modeling for human-like reasoning behaviors during information retrieval, and (2) reliance on suboptimal medical corpora, which often results in the retrieval of irrelevant or noisy snippets. To overcome these challenges, we propose Discuss-RAG, a plug-and-play module designed to enhance the medical QA RAG system through collaborative agent-based reasoning. Our method introduces a summarizer agent that orchestrates a team of medical experts to emulate multi-turn brainstorming, thereby improving the relevance of retrieved content. Additionally, a decision-making agent evaluates the retrieved snippets before their final integration. Experimental results on four benchmark medical QA datasets show that Discuss-RAG consistently outperforms MedRAG, especially significantly improving answer accuracy by up to 16.67% on BioASQ and 12.20% on PubMedQA. The code is available at: https://github.com/LLM-VLM-GSL/Discuss-RAG.
title Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
topic Computation and Language
url https://arxiv.org/abs/2504.21252