Xiaomi-GUI-0 Technical Report
Graphical user interface (GUI) agents build on vision-language models to complete user tasks end-to-end in real applications through interface actions such as tapping, swiping, text entry, and navigation. However, existing GUI agents are trained and evaluated largely on offline trajectories, simulated environments, and standardized benchmarks. These differ substantially from real applications in interface layout, interaction logic, and abnormal-state distribution, and cannot faithfully characterize execution stability in real-world use, where account states, permission dialogs, payment authentication, and risk control continually reshape the state distribution and open a persistent gap be...
| Authors | Wanxia Cao, Chengzhen Duan, Pei Fu et al. |
|---|---|
| Primary category | cs.AI |
| Published | 30 June 2026 |
| Last updated at source | 1 July 2026 |
Popularity, last 3 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- SeerRay-Lab/RealMobileDataset · cited by
Models and datasets referencing this paper
- SeerRay-Lab/RealMobileDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 19 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.