Computer-use agents increasingly tackle tasks ranging from everyday desktop activities to long-horizon professional workflows. Yet interfaces centered on screenshots and mouse-and-keyboard actions can impose a human-interaction prior, requiring repeated screen interpretation while leaving the computer's semantic and pr...
Hao-Qing Wang, Xiao-Yi Zhang, Si-Cheng Fan et al.· 0 citations
This work introduces RobotWorld, a challenging simulation testbed for robot use: turning instructions and observations into physical task execution through robot interfaces, and analyses task outcomes alongside execution traces, identifying both the capabilities that transfer and the gaps that prevent reliable completi...
Zhiqin Yang, Chen-Xin Li, Xiao-Meng Hu et al.· 3 citations
This work proposes two classes of attacks: a static attack, which employs a fixed injection prompt, and an iterative attack, which optimizes the injection prompt against a simulated reviewer model to maximize its effectiveness.
Qing Zhou, Zhexin Zhang, Zhi Li et al.· arXiv.org· 6 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.