Alibaba's Qwen-UI-Agent: SOTA on Mobile Use, Beats GPT-4o
AlibabaTongyiLab · hf · 2026-07-31
Alibaba's Tongyi Lab released the technical report for Qwen-UI-Agent, a real-world centric foundation GUI agent designed to operate reliably across mobile, computer, web, and DeepSearch environments.
- Architecture: Features a unified action space interleaving GUI operations with CLI execution and batched actions. It combines sandbox environments with a large-scale real-device mobile runtime and an AutoResearch-style data flywheel.
- RL Training: Supports online reinforcement learning on trajectories exceeding 100 turns, accelerated by over 10,000 concurrent environments.
- Performance: Sets SOTA on mobile-use benchmarks (92.2% on MobileWorld-Real). Achieves 79.5% on OSWorld-Verified for computer use, beating frontier models including Opus 3.5, Gemini 1.5 Pro, and GPT-4o.
More from coding & agent
- OpenSwiftUI: An Open Source Implementation of Apple's UI Framework — tom_doerr · 2026-07-31
- Practical Tip: Use AI to Generate Controllable Structures Instead of Final Products — jmugan · 2026-07-31
- Giving AI Agents Modal Compute Tokens: Train Models, Don't Hack the Pentagon — drscotthawley · 2026-07-31
- AI Runs 'Zero-Person Company' for 24 Hours, Burns Cash and Buys Fake Users — 机器之心 · 2026-07-31
- External AI Agent Connects to Game via MCP to Generate Card Match Replays — tristanbob · 2026-07-31
- Developer Shares Round 2 Progress of ZDC Agent Workflow Experiment — doodlestein · 2026-07-31