Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use

原文：Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use

作者：Yanzhe Chen, Ziyi Yang, Jifeng Zhu, Qiming Huang, Ruihe An, Peiyao Xu, Hesen Yang, Runda Liu, Chang Gong, Zhijun Cao, Zechen Bai, Wenzheng Zeng, Yiqi Lin, Guoqiang Liang, Kevin Yuchen Ma, Kevin Qinghong Lin, Mike Zheng Shou

来源：arXiv cs.AI（人工智能）

正文

Computer Science > Robotics

arXiv:2610.30108v1 (cs)

[Submitted on 21 Oct 2026]

Title:Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use

Authors:Yanzhe Chen, Ziyi Yang, Jifeng Zhu, Qiming Huang, Ruihe An, Peiyao Xu, Hesen Yang, Runda Liu, Chang Gong, Zhijun Cao, Zechen Bai, Wenzheng Zeng, Yiqi Lin, Guoqiang Liang, Kevin Yuchen Ma, Kevin Qinghong Lin, Mike Zheng Shou

View a PDF of the paper titled Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use, by Yanzhe Chen and 16 other authors

View PDF

HTML (experimental)

Abstract:Multimodal agents (MMAs) sustain interaction through reasoning, memory, tools, and feedback, most visibly as computer-use agents, while robotic systems (RSs) couple sensing and actuation under physical dynamics. We define multimodal embodied agents (MMEAs) as goal-directed systems that couple multimodal task reasoning with physical action and revise decisions from the resulting feedback. This raises a central question: what changes when a multimodal agent moves from computer-use to robot-use? We introduce PAPAV, a unified capability-centric framework of five recurring functions: Perceive the current state, Anticipate action effects, Plan a feasible course, Act through an interface or body, and Verify the outcome. Defined by function rather than architecture, these capabilities let PAPAV identify what all three share and then compare MMEAs with MMAs and with RSs. Five physical constraints, from partial observability to unverifiable outcomes, leave fewer choices fixed in advance and less room to reverse errors. Across 64 benchmarks, explicit evaluation centers on Act; only 5 assess Anticipate and 3 assess Verify, leaving both largely hidden behind task success. These constraints also frame the open challenges we identify. PAPAV therefore provides a common basis for designing reliable physical agents and measuring progress across all five capabilities rather than task success alone.

Comments:

Project website: this https URL

Subjects:

Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Multiagent Systems (cs.MA); Multimedia (cs.MM)

Cite as:

arXiv:2610.30108 [cs.RO]

(or

arXiv:2610.30108v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2610.30108

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

机器人 · 人工智能 · 计算机视觉 · 多智能体 · cs.MM

由「前沿雷达」于 2026-10-22 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。