Alibaba's Qwen-UI-Agent, a new GUI agent foundation model, has been released to control devices across various screens including phones, desktops, and the web. This model is designed to read screens and perform actions like clicks and swipes, demonstrating strong performance on benchmarks such as MobileWorld and OSWorld-Verified. Qwen-UI-Agent also incorporates a safety feature that requires user confirmation before executing sensitive actions like payments. AI
IMPACT Enables AI agents to interact with graphical user interfaces across multiple device types.
RANK_REASON Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
