arXiv cs.AI· Di Zhu, Yu Yvonne Wu, Hong Jia, Aaqib Saeed, Vassilis Kostakos, Ting Dang·· 14 小时前AI 评分31
VitalAgent：基于可穿戴健康数据的反应式与主动式生理监测工具增强智能体
VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data
AI 导读
VitalAgent 是一个面向 ECG/PPG 可穿戴数据的工具增强智能体框架，同时支持反应式问答与主动式监测。研究团队构建了 VitalBench 基准，含 1,862 个问答对和 90.2 小时连续 ECG/PPG 记录，覆盖心脏、身体活动与压力相关任务。实验显示其在反应式评测中较提示词与智能体基线提升超过 25 个绝对点，并能在长期生理信号上实现主动告警监测。
正文 · 原文
Abstract:Wearable devices provide continuous access to physiological signals such as ECG and PPG, offering a path to answering users' questions about their own physiological state and to early detection of cardiac and physiological abnormalities. Yet existing mobile health (mHealth) systems are largely limited to task-specific prediction pipelines or reactive question answering over static summaries. They lack the temporal reasoning, persistent physiological context, and proactive monitoring required for long-term signal streams. To advance this setting, we introduce VitalBench, a longitudinal physiological monitoring benchmark comprising 1,862 QA pairs for reactive question answering and 90.2 hours of continuous ECG/PPG recordings for proactive monitoring, covering cardiac, physical activity, and stress-related tasks. Building on this resource, we propose VitalAgent, a tool-augmented agentic framework for ECG/PPG-based mHealth that supports both reactive question answering and proactive monitoring. VitalAgent is built on a longitudinal physiological memory and a tool-augmented reasoning interface that enables dynamic computation over raw signals. Experiments demonstrate that VitalAgent achieves over 25 points absolute improvement over prompt-based and agentic baselines in reactive evaluation and enables proactive alert monitoring over long-term physiological signals, pointing toward mHealth systems that can both answer questions about and continuously monitor a person's physiological state beyond the clinic.
| Comments: | Accepted at the GenAI for Health Workshop @ NeurIPS 2026 (GenAI4Health). v3: camera-ready version with revised proactive monitoring experiments. 25 pages, 3 figures, 13 tables |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.29483 [cs.AI] |
| (or arXiv:2605.29483v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.29483 arXiv-issued DOI via DataCite |
Submission history
From: Di Zhu [view email]
[v1]
Thu, 28 May 2026 07:10:14 UTC (150 KB)
[v2]
Thu, 18 Jun 2026 11:19:35 UTC (160 KB)
[v3]
Mon, 26 Oct 2026 11:26:24 UTC (132 KB)
来源：arXiv cs.AI · arxiv.org