# MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language Models

arXiv: https://arxiv.org/abs/2509.23725 · HTML: https://mlsanity.com/paper/2509.23725/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 19 of 19)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making](https://mlsanity.com/paper/2404.15155/) (2024)
- [Deep Bidirectional Language-Knowledge Graph Pretraining](https://mlsanity.com/paper/2210.09338/) (2022)
- [MMedAgent: Learning to Use Medical Tools with Multi-modal Agent](https://mlsanity.com/paper/2407.02483/) (2024)
- [Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2408.04187/) (2024)
- [ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph](https://mlsanity.com/paper/2403.00839/) (2024)
- [Biomedical knowledge graph-optimized prompt generation for large language models](https://mlsanity.com/paper/2311.17330/) (2023)
- [MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models](https://mlsanity.com/paper/2409.15477/) (2024)
- [KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA](https://mlsanity.com/paper/2410.04660/) (2024)
- [Piecewise-Velocity Model for Learning Continuous-time Dynamic Node Representations](https://mlsanity.com/paper/2212.12345/) (2022)
- [Reliable and diverse evaluation of LLM medical knowledge mastery](https://mlsanity.com/paper/2409.14302/) (2024)

## Built on by (most cited first, 9 of 9)

- [FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering](https://mlsanity.com/paper/2601.06992/) (2026)
- [MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems](https://mlsanity.com/paper/2603.09909/) (2026)
- [Perceive and Calibrate: Analyzing and Enhancing Robustness of Medical Multi-Modal Large Language Models](https://mlsanity.com/paper/2512.21964/) (2025)
- [A Medical Multimodal Diagnostic Framework Integrating Vision-Language Models and Logic Tree Reasoning](https://mlsanity.com/paper/2512.21583/) (2025)
- [Adapting 2D Multi-Modal Large Language Model for 3D CT Image Analysis](https://mlsanity.com/paper/2604.10233/) (2026)
- [MedCollab: IBIS-Guided Multi-Agent Collaboration with Hierarchical Disease Relation Chains for Clinical Diagnosis](https://mlsanity.com/paper/2603.01131/) (2026)
- [Med-Evo: Test-time Self-evolution for Medical Multimodal Large Language Models](https://mlsanity.com/paper/2603.07443/) (2026)
- [Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures](https://mlsanity.com/paper/2604.18133/) (2026)
- [Evidence, Logic, and Compliance: Multi-Agent Structured Graph Reasoning with Expert Arbitration for Medical Referral](https://mlsanity.com/paper/2608.30938/) (2026)

## Abstract (arXiv)

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 textscMedLA, 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 textscMedLA consistently outperforms both static role-based systems and single-agent baselines on challenging benchmarks such as MedDDx and standard medical QA tasks. Furthermore, textscMedLA 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.