Xiaomi-GUI-0 Technical Report
- Published
- Source
- arXiv
- Paper number
- 529
- Field
- AI / General
- arXiv ID
- 2606.31410
Key points
- A hybrid, real-device-centered infrastructure uses physical devices as the main environment and a sandbox as a secondary one to match the real deployment distribution.
- An error-driven data flywheel turns failed rollout trajectories into corrective actions, reflection explanations, and recovery demonstrations.
- A three-stage progressive curriculum: SFT for basic operations, Step RL for long-term planning, and Agentic RL for error recovery.
- It achieves a 72.0% success rate on RealMobile and 78.9% on AndroidWorld.
- It strengthens the ability to handle abnormal states in real applications, including account states, permission dialogs, payment authentication, and risk controls.
- It builds a closed-loop real-device environment to solve emulator-detection mechanisms.
Paper links
External research summaries. These are not HDATF publications or measured product results.