MedConMA: A Confidence-Driven Multi-agent Framework for Medical Q&A

Wang, R; Chen, Y; Zhang, W; Si, J; Guan, H; Peng, X; Lu, W

MedConMA: A Confidence-Driven Multi-agent Framework for Medical Q&A

Wang, R Chen, Y Zhang, W Si, J Guan, H Peng, X

Lu, W

Permalink

Publisher:: Springer Nature
Publication Type:: Conference Proceeding
Citation:: Lecture Notes in Computer Science, 2025, 15872 LNAI, pp. 421-433
Issue Date:: 2025-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted versionAdobe PDF (5.15 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Wang, R
dc.contributor.author	Chen, Y
dc.contributor.author	Zhang, W
dc.contributor.author	Si, J
dc.contributor.author	Guan, H
dc.contributor.author	Peng, X https://orcid.org/0000-0002-8901-1472
dc.contributor.author	Lu, W
dc.date.accessioned	2025-09-08T04:00:09Z
dc.date.available	2025-09-08T04:00:09Z
dc.date.issued	2025-01-01
dc.identifier.citation	Lecture Notes in Computer Science, 2025, 15872 LNAI, pp. 421-433
dc.identifier.isbn	9789819681792
dc.identifier.issn	0302-9743
dc.identifier.issn	1611-3349
dc.identifier.uri	http://hdl.handle.net/10453/189672
dc.description.abstract	Medical Q&A tasks aim to address healthcare questions by analyzing medical data, playing a critical role in supporting patient care and informed decision-making. Recent research on LLMs in medical Q&A tasks underscores their potential to tackle complex medical questions through advanced reasoning and the integration of external knowledge. However, these studies predominantly emphasize complex questions, often overlooking simpler ones, which leads to increased computational overhead and higher risks of inaccuracies. To overcome these challenges, we propose a multi-agent framework that differentiates between complex and simple questions by leveraging confidence scores generated by distinct agents. The framework dynamically generates domain-specific agents that assess question difficulty based on confidence scores, allowing for the application of tailored processing strategies. Ultimately, agents converge on a final answer through a voting mechanism. Our approach demonstrates significant improvements across eight datasets, highlighting the effectiveness of the proposed framework. Our code can be found at https://github.com/w1031343245/MedConMA.git.
dc.language	en
dc.publisher	Springer Nature
dc.relation.ispartof	Lecture Notes in Computer Science
dc.relation.ispartofseries	Lecture Notes in Computer Science
dc.relation.isbasedon	10.1007/978-981-96-8180-8_33
dc.rights	info:eu-repo/semantics/openAccess
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.classification	46 Information and computing sciences
dc.title	MedConMA: A Confidence-Driven Multi-agent Framework for Medical Q&A
dc.type	Conference Proceeding
utslib.citation.volume	15872 LNAI
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Australian Artificial Intelligence Institute (AAII)
utslib.copyright.status	open_access	*
dc.date.updated	2025-09-08T04:00:02Z
pubs.publication-status	Published
pubs.volume	15872 LNAI

Abstract:

Medical Q&A tasks aim to address healthcare questions by analyzing medical data, playing a critical role in supporting patient care and informed decision-making. Recent research on LLMs in medical Q&A tasks underscores their potential to tackle complex medical questions through advanced reasoning and the integration of external knowledge. However, these studies predominantly emphasize complex questions, often overlooking simpler ones, which leads to increased computational overhead and higher risks of inaccuracies. To overcome these challenges, we propose a multi-agent framework that differentiates between complex and simple questions by leveraging confidence scores generated by distinct agents. The framework dynamically generates domain-specific agents that assess question difficulty based on confidence scores, allowing for the application of tailored processing strategies. Ultimately, agents converge on a final answer through a voting mechanism. Our approach demonstrates significant improvements across eight datasets, highlighting the effectiveness of the proposed framework. Our code can be found at https://github.com/w1031343245/MedConMA.git.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/189672