arXiv：cs.AI· Zhenhua Yang, Jiafeng Liang, Xingyu Zhou, Yi Jiang, Xiayu Cao, Zui Chen, Luqi Wang, Haiyang Sun, Yufei Xiang, Chang Li, Rongchuan Mu, Bowen Chi, Zihe Tong, Mingyu Li, Huijie Ma, Yiqiao Yang, Baoqi Ren, Zhiming Ma, Zhihao Zhu, Jiahao Ji, Zhuoyao Wang, Qianyu Wang, Xiangyu Liu, Wang Zixiang, Shunliang Zhang, Ming Liu, Xiaocheng Feng, Duyu Tang, Bing Qin·· 22 小时前
ProAgent：持续观察与适时干预的主动式物理 AI 系统
Proactive Physical AI through Continuous Observation and Timely Intervention
AI 导读
研究提出主动式物理 AI（Proactive Physical AI）问题，即 AI 系统持续观察物理世界、识别需要干预的情境并及时发起行动，而非等待明确任务指令。
正文
Authors:Zhenhua Yang, Jiafeng Liang, Xingyu Zhou, Yi Jiang, Xiayu Cao, Zui Chen, Luqi Wang, Haiyang Sun, Yufei Xiang, Chang Li, Rongchuan Mu, Bowen Chi, Zihe Tong, Mingyu Li, Huijie Ma, Yiqiao Yang, Baoqi Ren, Zhiming Ma, Zhihao Zhu, Jiahao Ji, Zhuoyao Wang, Qianyu Wang, Xiangyu Liu, Wang Zixiang, Shunliang Zhang, Ming Liu, Xiaocheng Feng, Duyu Tang, Bing Qin
Abstract:Physical AI is commonly formulated around an explicitly specified task: given a goal or instruction, a system perceives, reasons, and acts. In many real-world settings, however, important tasks emerge from continuously changing world states before a person explicitly formulates them. We study this complementary problem as Proactive Physical AI, where an AI system continuously observes the physical world, identifies situations that warrant intervention, and initiates appropriate actions at the right time. We develop ProAgent, an end-to-end system built around two components: a Jev-style proactive timing model (dubbed StreamingJev) that determines whether and when intervention is needed, and a Response Model that generates responses for people or invokes available device capabilities for physical execution. To support learning at scale, we develop an automated data pipeline that converts videos into supervision for proactive timing. Experiments demonstrate strong proactive performance under both explicit objectives and standing roles, combining more accurate intervention timing with fewer false triggers than the source-backbone baseline. Real-robot evaluations further demonstrate ProAgent's ability to identify emerging needs and translate them into appropriate physical actions.
| Comments: | 33 pages, 5 figures, including appendices |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO) |
| Cite as: | arXiv:2610.16967 [cs.CV] |
| (or arXiv:2610.16967v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16967 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhenhua Yang [view email]
[v1]
Mon, 12 Oct 2026 15:33:34 UTC (5,128 KB)
来源：arXiv：cs.AI · arxiv.org