arXiv cs.AI· Weiwei Ma, Xiaobing Yu, Peijie Qiu, Jin Yang, Zhaoqi An, Xuanzhao Dong, Xiaoqi Zhao, Xiaofeng Liu·· 9 天前AI 评分28
ActiveMedAgent：面向多模态医疗诊断的成本感知轨迹学习
ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis
AI 导读
ActiveMedAgent 提出一种成本感知的序贯诊断框架，在冻结的 API 视觉语言模型上追踪候选诊断概率分布，并按每步诊断效用减去成本对证据采集打分，再用轻量 MLP 控制器离线学习何时追加证据、何时给出结论。在三个常用基准上，基于轨迹的策略学习持续优于无引导采集和全模态基线；研究还发现信息过载效应，175 个案例中智能体用更少通道即得出正确诊断，而全模态基线失败。
正文 · 原文
Abstract:Clinical diagnosis is inherently sequential: clinicians escalate from cheap to costly tests only when additional evidence is expected to resolve diagnostic uncertainty. We present ActiveMedAgent, a framework that brings this cost-aware sequential logic to multimodal medical AI. Given a frozen, API-accessed vision-language model, ActiveMedAgent tracks probability distributions over candidate diagnoses and scores each acquisition by its per-step diagnostic utility minus cost. A lightweight MLP controller is then trained offline on these scored trajectories, learning when to request additional evidence and when to commit. Across three commonly used benchmarks, trajectory-based policy learning consistently outperforms both unguided acquisition and full-modality baselines. Notably, we identify an information overload effect. In 175 cases, the agent produces a correct diagnosis with fewer channels while the full-modality baseline fails, showing that learning what to omit can be as important as learning what to acquire.
| Comments: | EMNLP 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM) |
| Cite as: | arXiv:2610.11140 [cs.LG] |
| (or arXiv:2610.11140v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11140 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xiaofeng Liu [view email]
[v1]
Thu, 8 Oct 2026 03:06:11 UTC (459 KB)
来源：arXiv cs.AI · arxiv.org