arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.09018cs.AI
收藏

Meissa:多模态医疗代理智能

Meissa: Multi-modal Medical Agentic Intelligence

Johns Hopkins University(约翰霍普金斯大学);Cornell University(康奈尔大学)

Yixiong Chen, Xinyi Bai, Yue Pan, Zongwei Zhou, Alan Yuille

AI总结:

Meissa是一种轻量级多模态医疗代理智能模型,通过离线学习策略选择与执行,实现高效医疗决策。

摘要:

多模态大语言模型(MM-LLMs)在医学图像理解和临床推理中表现出强大的性能。最近的医疗代理系统通过增加工具使用和多代理协作扩展了它们,使复杂决策成为可能。然而,这些系统几乎完全依赖于前沿模型(例如GPT),其基于API的部署导致高成本、高延迟和隐私风险,这些风险与本地临床需求相冲突。我们提出了Meissa,一个轻量级的400亿参数医学MM-LLM,能够离线带来代理能力。与模仿静态答案不同,Meissa通过从前沿模型中提炼结构化轨迹学习何时进行外部交互(策略选择)以及如何执行多步骤交互(策略执行)。具体而言,我们提出:(1)统一轨迹建模:轨迹(推理和行动轨迹)在单一状态-动作-观察形式中表示,允许一个模型在异构医疗环境中泛化。(2)三级分层监督:模型自身的错误会触发从直接推理到工具增强和多代理交互的逐步升级,明确学习难度感知的策略选择。(3)前瞻性-回顾性监督:将探索性的前向轨迹与 hindsight-理性化的执行轨迹配对,使有效交互策略的学习更加稳定。在40000条精心编纂的轨迹上训练,Meissa在13个涵盖放射学、病理学和临床推理的医学基准测试中16个评估设置中匹配或超越了专有前沿代理。与典型前沿模型如Gemini-3相比,Meissa的参数数量减少了25倍以上,能够在完全离线的情况下运行,端到端延迟比基于API的部署低22倍。数据、模型和环境已发布在https://github.com/Schuture/Meissa。

英文摘要:

Multi-modal large language models (MM-LLMs) have shown strong performance in medical image understanding and clinical reasoning. Recent medical agent systems extend them with tool use and multi-agent collaboration, enabling complex decision-making. However, these systems rely almost entirely on frontier models (e.g., GPT), whose API-based deployment incurs high cost, high latency, and privacy risks that conflict with on-premise clinical requirements. We present Meissa, a lightweight 4B-parameter medical MM-LLM that brings agentic capability offline. Instead of imitating static answers, Meissa learns both when to engage external interaction (strategy selection) and how to execute multi-step interaction (strategy execution) by distilling structured trajectories from frontier models. Specifically, we propose: (1) Unified trajectory modeling: trajectories (reasoning and action traces) are represented within a single state-action-observation formalism, allowing one model to generalize across heterogeneous medical environments. (2) Three-tier stratified supervision: the model's own errors trigger progressive escalation from direct reasoning to tool-augmented and multi-agent interaction, explicitly learning difficulty-aware strategy selection. (3) Prospective-retrospective supervision: pairing exploratory forward traces with hindsight-rationalized execution traces enables stable learning of effective interaction policies. Trained on 40K curated trajectories, Meissa matches or exceeds proprietary frontier agents in 10 of 16 evaluation settings across 13 medical benchmarks spanning radiology, pathology, and clinical reasoning. Using over 25x fewer parameters than typical frontier models like Gemini-3, Meissa operates fully offline with 22x lower end-to-end latency compared to API-based deployment. Data, models, and environments are released at https://github.com/Schuture/Meissa.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑