Qwen-UI-Agent

Qwen-UI-Agent is a real-world-centric foundation GUI agent designed to unify mobile, computer, browser, and DeepSearch scenarios into a single model. It enables autonomous task execution across platforms by combining GUI interaction with CLI execution, proactive service initiation, and long-horizon planning.

Qwen-UI-Agent is a real-world-centric foundation GUI agent designed to unify mobile, computer, browser, and DeepSearch scenarios into a single model. It enables autonomous task execution across platforms by combining GUI interaction with CLI execution, proactive service initiation, and long-horizon planning.

• 01Unified GUI and CLI action space for cross-platform task execution
• 02Real-device training and evaluation on 100+ physical smartphones
• 03AutoResearch-style data flywheel for autonomous capability improvement
• 04Proactive service initiation based on real-world signals
• 05Scalable long-horizon online reinforcement learning
• 06State-of-the-art performance on major GUI benchmarks like MobileWorld and WebArena