Alibaba Tongyi Lab Releases MAI-UI: A Foundation GUI Agent Family that Surpasses Gemini 2.5 Pro, Seed1.8 and UI-Tars-2 on AndroidWorld

Alibaba Tongyi Lab unveiled MAI-UI, a foundation GUI agent family that outperforms Gemini 2.5 Pro, Seed 1.8, and UI-TARS-2 on AndroidWorld benchmarks. The system integrates native MCP tool use, agent-user interaction, device-cloud collaboration, and online reinforcement learning. MAI-UI addresses three key gaps in early GUI agents, achieving state-of-the-art results in general GUI grounding and mobile navigation tasks.