EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

BioRAGent: natural language biomedical querying with retrieval-augmented multiagent systems

Manlian Bi, Zhijie Bao, Dongna Xie, Xiaohan Xie, Changxiao Yang, Tao Wang, Yongtian Wang, Jiajie Peng

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf539 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Manlian Bi und 7 weiteren Autor:innen. Beteiligte Einrichtung: AI for Science Interdisciplinary Research Center, School of Computer Science, Northwestern Polytechnical University, No. 1 Dongxiang Road, Xi'an 7101…. Hauptthemen laut MEDLINE: Natural Language Processing, Information Storage and Retrieval, Software, Computational Biology. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Understanding the roles of genes, phenotypes, and diseases is crucial for advancing biomedical research. However, efficient and accessible retrieval of biomedical knowledge remains a challenge due to the complexity of the relevant data. We introduce BioRAGent, an intelligent biomedical assistant that combines Tool-augmented retrieval-augmented generation (RAG) with a multiagent system. Leveraging the ability of large language models, BioRAGent facilitates natural language queries about genes, phenotypes, diseases, and their interrelationships. BioRAGent employs three specialized agents: Guide (query optimization), Retriever (data retrieval), and Reviewer (answer validation) to access authoritative biomedical databases and to generate accurate responses. We evaluate the performance of BioRAGent on a benchmark of eleven single-hop and three multi-hop tasks, demonstrating superior results compared with state-of-the-art models. User evaluations highlight the practicality and robust user experience of BioRAGent, particularly in handling complex multi-hop queries. Moreover, ablation experiments validate the contribution of each agent in improving retrieval accuracy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingInformation Storage and RetrievalSoftwareComputational BiologyHumansAlgorithmsDatabases, Factual

Stichwörter der Autor:innen

biomedical knowledge retrievallarge language modelsmultiagent systemretrieval-augmented generation

Autor:innen und Institutionen

  • AI for Science Interdisciplinary Research Center, School of Computer Science, Northwestern Polytechnical University, No. 1 Dongxiang Road, Xi'an 710129, China.
  • Key Laboratory of Big Data Storage and Management, Ministry of Industry and Information Technology, Northwestern Polytechnical University, No. 1 Dongxiang Road, Xi'an 710129, China.
  • School of Data Science, Fudan University, No. 220 Handan Road, Shanghai 200433, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Bi, M., Bao, Z., Xie, D., Xie, X., Yang, C., Wang, T., Wang, Y., & Peng, J. (2025). BioRAGent: natural language biomedical querying with retrieval-augmented multiagent systems. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf539

Vancouver

Bi M, Bao Z, Xie D, Xie X, Yang C, Wang T, et al. BioRAGent: natural language biomedical querying with retrieval-augmented multiagent systems. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf539

BibTeX
@article{Bi2025,
  author = {Bi, Manlian and Bao, Zhijie and Xie, Dongna and Xie, Xiaohan and Yang, Changxiao and Wang, Tao and Wang, Yongtian and Peng, Jiajie},
  title = {BioRAGent: natural language biomedical querying with retrieval-augmented multiagent systems},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf539}
}
Kostenlos starten →