← 研踪 PaperTrailCVF · CVPR 2026:cvf:506147ebd7e0a4a2530927f5b68f7ee1 · 记录 #1
MMBench-GUI: A Unified Hierarchical Evaluation Framework for Multi-Platform GUI Agents
Wang, XuehuiWu, ZhenyuXie, JingJingDing, ZichenYang, BowenLi, ZehaoLiu, ZhaoyangLi, QingyunDong, XuanChen, ZheWang, WeiyunZhao, XiangyuChen, JixuanDuan, HaodongXie, TianbaoYang, ChenyuSu, ShiqianYu, YueZhang, YantingYue, XiangyuSu, WeijieZhu, XizhouShen, WeiDai, JifengWang, Wenhai 来源日期(仅到年份) 2026
来源记录日期 2026
雷达观测 2026-11-05 03:01
摘要
We introduce MMBench-GUI, a hierarchical benchmark for evaluating GUI automation agents across Windows, macOS, Linux, iOS, Android, and Web. The benchmark spans four levels: Content Understanding, Element Grounding, Task Automation, and Task Collaboration, covering essential skills for GUI agents. To assess both effectiveness and efficiency, we further propose the Efficiency-Quality-Aware (EQA) metric, which measures task success alongside action redundancy. Extensive evaluations reveal that precise visual grounding is the critical determinant of performance, underscoring the advantages of modular designs with specialized grounding modules. Moreover, all agents suffer from substantial inefficiencies, frequently completing tasks with excessive steps despite eventual success. Performance also degrades on complex or cross-application tasks, exposing weaknesses in memory, planning, and adaptive reasoning. By providing broad coverage, standardized protocols, and novel metrics, MMBench-GUI establishes the first comprehensive foundation for advancing GUI agent research.
论文发现出处
这些页面提供论文线索,不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
MMBench-GUI: A Unified Hierarchical Evaluation Framework for Multi-Platform GUI Agents
We introduce MMBench-GUI, a hierarchical benchmark for evaluating GUI automation agents across Windows, macOS, Linux, iOS, Android, and Web. The benchmark spans four levels: Content Understanding, Element Grounding, Task Automation, and Task Collaboration, covering essential skills for GUI agents. To assess both effectiveness and efficiency, we further propose the Efficiency-Quality-Aware (EQA) metric, which measures task success alongside action redundancy. Extensive evaluations reveal that precise visual grounding is the critical determinant of performance, underscoring the advantages of modular designs with specialized grounding modules. Moreover, all agents suffer from substantial inefficiencies, frequently completing tasks with excessive steps despite eventual success. Performance also degrades on complex or cross-application tasks, exposing weaknesses in memory, planning, and adaptive reasoning. By providing broad coverage, standardized protocols, and novel metrics, MMBench-GUI establishes the first comprehensive foundation for advancing GUI agent research.
查看此版本解读 →查看此版本原文 ↗