外观
论文HF Daily Papers · arXiv 2610.301087 天前
PAPAV框架统一多模态具身智能体五维能力评估体系
本文由 AI 根据公开内容整理，可能有误，请以原文为准：Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use（HF Daily Papers · arXiv 2610.30108）
核心内容
研究定义了多模态具身智能体（MMEAs）为耦合多模态推理与物理动作的目标导向系统，并提出PAPAV统一能力中心框架。该框架包含感知当前状态、预测动作效应、规划可行路径、通过接口或本体执行、验证结果五大功能维度，旨在解决智能体从Computer-Use转向Robot-Use时的核心差异问题，为跨域系统设计提供通用基础。
论文指出物理环境存在部分可观测性及结果不可验证等五大约束，导致预设选项减少且纠错空间受限。对64个现有基准的审计显示，评测严重偏向Act维度，仅5个基准覆盖Anticipate能力，3个覆盖Verify能力。这种结构性缺失使得预测与验证能力被任务成功率掩盖，PAPAV框架据此确立了超越单一任务指标的五维全链路评估新范式。
关键看点
- PAPAV框架：定义Perceive、Anticipate、Plan、Act、Verify五维功能，解耦架构与能力以统一评测标准
- 基准审计：分析64个Benchmark发现仅5个评估预测、3个评估验证，Act维度评测占比过高
- 物理约束：归纳部分可观测性等五大限制，阐明Robot-Use相比Computer-Use的纠错空间缩减机制
- 评估范式：主张从单一任务成功率转向五维能力独立度量，解决预测与验证能力隐性化问题
工程与产业观察
该框架揭示了当前具身智能评测体系中“重执行、轻预测验证”的结构性短板。对于算法工程师，这提示需构建针对Anticipate和Verify的专项数据集与Metric；对产业决策者，意味着在选型或自研时，应关注系统在物理约束下的闭环校验能力而非仅看Demo成功率，这是决定机器人从实验室走向真实非结构化场景的关键工程壁垒。
英文摘要 (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.
Hugging Face Daily Papers 热度：15 upvotes 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 Qingho
来源
本页事实对应的公开页面，以原文为准。