cs.AISep 29, 2025

MedMMV: A Controllable Multimodal Multi-Agent Framework for Reliable and Verifiable Clinical Reasoning

Authors: Hongjun Liu, Yinghao Zhu, Yuhui Wang, Yitao Long, Lequan Yu, Chen Zhao

Organizations: New York University · NYU Shanghai · The University of Hong Kong · Independent Researcher

Abstract

Current multimodal large language models (MLLMs) suffer from unstable reasoning due to the lack of mechanisms for controlling reasoning trajectories, often leading to hallucinated conclusions. Our analysis reveals that early-stage uncertainty induces trajectory switching, significantly increasing hallucination risk. We propose MedMMV, an evidence-grounded trajectory control framework that treats reasoning as a search-and-selection process over candidate trajectories. By constructing, refining, and selecting among multiple reasoning paths, MedMMV improves reliability and produces structured supervision signals over trajectory quality. We further convert these signals into learnable objectives for post-training, including reject sampling and pairwise preference learning, enabling smaller models to learn trajectory selection as an efficient single-pass capability. Instead of merely imitating reasoning traces, the model is trained to assign higher likelihood to preferred trajectories. Experiments show that richer supervision leads to stronger transfer, with accuracy improving from 10.5% to 29.0%. Our results demonstrate that trajectory selection is the key transferable capability for reliable reasoning.

Figures & tables

Appendix figures & tables21 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Seeing Through the Chain: Understanding and Mitigating Hallucinations in Multimodal Large Reasoning Models

    Feb 3, 2026Hao Fang, Jinyu Li, Jiawei Kong +4Hallucination MitigationMultimodal Reasoning

  2. Synergistic Perception-Reasoning Governance: Grounding Medical MLLMs with Verifiable Anatomical Evidence

    Jun 30, 2026Rui Hao, Qiankun Li, Junyuan Mao +4Radiology Report GenerationMedical Visual Question Answering