Alibaba's Tongyi Lab just dropped MAI-UI, a new family of GUI agents that's outperforming Gemini 2.5 Pro and other top models on AndroidWorld benchmarks. What's interesting here is the integrated approach—combining MCP tool use, device-cloud collaboration, and online RL rather than treating these as separate problems. The GUI agent space is heating up fast, and this release addresses some real gaps in how these systems handle real-world mobile navigation.
WWW.MARKTECHPOST.COM
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 have released MAI-UI—a family of foundation GUI agents. It natively integrates MCP tool use, agent user interaction, device–cloud collaboration, and online RL, establishing state-of-the-art results in general GUI grounding and mobile GUI navigation, surpassing Gemini-2.5-Pro, Seed1.8, and UI-Tars-2 on AndroidWorld. The system targets three specific gaps that early GUI agents often ignore, […] The post Alibaba Tongyi Lab Releases MAI-UI: A Foundation GUI Agent Family
0 Σχόλια 0 Μοιράστηκε 56 Views
Zubnet https://www.zubnet.com