The development of GUI agents could revolutionize the next generation of human-computer interaction. Motivated by this vision, we present MAI-UI, a family of foundation GUI agents spanning the full spectrum of sizes, including 2B, 8B, 32B, and 235B-A22B variants. We identify four key challenges to realistic deployment: the lack of native agent–user interaction, the limits of UI-only operation, the absence of a practical deployment architecture, and brittleness in dynamic environments. MAI-UI addresses these issues with a unified methodology: a self-evolving data pipeline that expands the navigation data to include user interaction and MCP tool calls, a native device–cloud collaboration system that routes execution by task state, and an online RL framework with advanced optimizations to scale parallel environments and context length.
1# Install vLLM
2pip install vllm
3
4# Start vLLM API server
5python -m vllm.entrypoints.openai.api_server \
6 --model Tongyi-MAI/MAI-UI-8B \
7 --served-model-name MAI-UI-8B \
8 --host 0.0.0.0 \
9 --port 8000 \
10 --tensor-parallel-size 1 \
11 --trust-remote-code
MAI-UI establishes new state-of-the-art across GUI grounding and mobile navigation.
If you find this project useful for your research, please consider citing our work:
1@misc{zhou2025maiuitechnicalreportrealworld,
2 title={MAI-UI Technical Report: Real-World Centric Foundation GUI Agents},
3 author={Hanzhang Zhou and Xu Zhang and Panrong Tong and Jianan Zhang and Liangyu Chen and Quyu Kong and Chenglin Cai and Chen Liu and Yue Wang and Jingren Zhou and Steven Hoi},
4 year={2025},
5 eprint={2512.22047},
6 archivePrefix={arXiv},
7 primaryClass={cs.CV},
8 url={https://arxiv.org/abs/2512.22047},
9}
