paper-with-me

Papers

MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration

2025-06-24 · Yucheng Zhou, Lingran Song, Jianbing Shen

Recent advancements in medical Large Language Models (LLMs) have showcased their powerful reasoning and diagnostic capabilities. Despite their success, current unified multimodal medical LLMs face limitations in knowledge update costs, comprehensiveness, and flexibility. To address these challenges, we introduce the Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis (MAM). Inspired by our empirical findings highlighting the benefits of role assignment and diagnostic discernment in LLMs, MAM decomposes the medical diagnostic process into specialized roles: a General Practitioner, Specialist Team, Radiologist, Medical Assistant, and Director, each embodied by an LLM-based agent. This modular and collaborative framework enables efficient knowledge updates and leverages existing medical LLMs and knowledge bases. Extensive experimental evaluations conducted on a wide range of publicly accessible multimodal medical datasets, incorporating text, image, audio, and video modalities, demonstrate that MAM consistently surpasses the performance of modality-specific LLMs. Notably, MAM achieves significant performance improvements ranging from 18% to 365% compared to baseline models. Our code is released at https://github.com/yczhou001/MAM.

📄 PDF Abstract BibTeX arXiv:2506.19835

Code (1)

yczhou001/mam 공식 구현 pytorch

Tasks

DiagnosticMedical Diagnosis

Similar Papers 제목 키워드 기반

Agent-Based Modular Learning for Multimodal Emotion Recognition in Human-Agent Systems

2025-12-02 · Matvey Nepomnyaschiy, Oleg Pereziabov, Anvar Tliamov, Stanislav Mikhailov 외 arxiv

Effective human-agent interaction (HAI) relies on accurate and adaptive perception of human emotional states. While multimodal deep learning models - leveraging facial expressions, speech, and textual cues - offer high a…

Multimodal Emotion RecognitionMultimodal Deep Learning

Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration

2025-11-24 · James Y. Huang, Sheng Zhang, Qianchu Liu, Guanghui Qin 외 arxiv

Large Language Models (LLMs) have demonstrated remarkable capabilities in challenging, knowledge-intensive reasoning tasks. However, extending LLMs to perceive and reason over a new modality (e.g., vision), often require…

Multimodal Reasoning

A modular architecture for creating multimodal agents

2022-06-01 · Thomas Baier, Selene Baez Santamaria, Piek Vossen

The paper describes a flexible and modular platform to create multimodal interactive agents. The platform operates through an event-bus on which signals and interpretations are posted in a sequence in time. Different sen…

MultiPress: A Multi-Agent Framework for Interpretable Multimodal News Classification

2026-04-04 · Tailong Luo, Hao Li, Rong Fu, Xinyue Jiang 외 arxiv

With the growing prevalence of multimodal news content, effective news topic classification demands models capable of jointly understanding and reasoning over heterogeneous data such as text and images. Existing methods …

News Classification

Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspective

2025-05-27 · Krishna Singh Rajput, Tejas Anvekar, Chitta Baral, Vivek Gupta

Recent advances in multimodal question answering have primarily focused on combining heterogeneous modalities or fine-tuning multimodal large language models. While these approaches have shown strong performance, they of…

Language ModelingLanguage ModellingLarge Language ModelQuestion Answering