AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

ADeptS-Bench: Measuring the Trustworthiness of Computer Use Agents Across Devices

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Computer Use Agents (CUAs) are increasingly deployed to navigate mobile and desktop applications on behalf of users, yet no benchmark comprehensively evaluates whether they can safely interact with visual interfaces while handling ambiguous instructions. We introduce ADeptS-Bench, a dual-stream trustworthiness benchmark, grounded in the ADEPTS capability framework and general population user studies. The Safety stream provides paired benign/malicious tasks with threats embedded in the visual interface. The Disambiguation stream evaluates whether agents seek clarification when intent is ambiguo

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T09:42:05.193Z. This is not the publication date.