Saved in:
Bibliographic Details
Main Authors: Ma, Siqi, Huang, Jiajie, Zhang, Fan, Shen, Yue, Wu, Jinlin, Fan, Guohui, Zhang, Zhu, Zang, Zelin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.23725
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915829463908352
author Ma, Siqi
Huang, Jiajie
Zhang, Fan
Shen, Yue
Wu, Jinlin
Fan, Guohui
Zhang, Zhu
Zang, Zelin
author_facet Ma, Siqi
Huang, Jiajie
Zhang, Fan
Shen, Yue
Wu, Jinlin
Fan, Guohui
Zhang, Zhu
Zang, Zelin
contents Answering complex medical questions requires not only domain expertise and patient-specific information, but also structured and multi-perspective reasoning. Existing multi-agent approaches often rely on fixed roles or shallow interaction prompts, limiting their ability to detect and resolve fine-grained logical inconsistencies. To address this, we propose \textsc{MedLA}, a logic-driven multi-agent framework built on large language models. Each agent organizes its reasoning process into an explicit logical tree based on syllogistic triads (major premise, minor premise, and conclusion), enabling transparent inference and premise-level alignment. Agents engage in a multi-round, graph-guided discussion to compare and iteratively refine their logic trees, achieving consensus through error correction and contradiction resolution. We demonstrate that \textsc{MedLA} consistently outperforms both static role-based systems and single-agent baselines on challenging benchmarks such as MedDDx and standard medical QA tasks. Furthermore, \textsc{MedLA} scales effectively across both open-source and commercial LLM backbones, achieving state-of-the-art performance and offering a generalizable paradigm for trustworthy medical reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23725
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language Models
Ma, Siqi
Huang, Jiajie
Zhang, Fan
Shen, Yue
Wu, Jinlin
Fan, Guohui
Zhang, Zhu
Zang, Zelin
Artificial Intelligence
Answering complex medical questions requires not only domain expertise and patient-specific information, but also structured and multi-perspective reasoning. Existing multi-agent approaches often rely on fixed roles or shallow interaction prompts, limiting their ability to detect and resolve fine-grained logical inconsistencies. To address this, we propose \textsc{MedLA}, a logic-driven multi-agent framework built on large language models. Each agent organizes its reasoning process into an explicit logical tree based on syllogistic triads (major premise, minor premise, and conclusion), enabling transparent inference and premise-level alignment. Agents engage in a multi-round, graph-guided discussion to compare and iteratively refine their logic trees, achieving consensus through error correction and contradiction resolution. We demonstrate that \textsc{MedLA} consistently outperforms both static role-based systems and single-agent baselines on challenging benchmarks such as MedDDx and standard medical QA tasks. Furthermore, \textsc{MedLA} scales effectively across both open-source and commercial LLM backbones, achieving state-of-the-art performance and offering a generalizable paradigm for trustworthy medical reasoning.
title MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language Models
topic Artificial Intelligence
url https://arxiv.org/abs/2509.23725