MAI-UI: Real-World Centric Foundation GUI Agents.
-
Updated
Dec 31, 2025 - HTML
MAI-UI: Real-World Centric Foundation GUI Agents.
Benchmark of complex, multimodal desktop-oriented tasks for advanced GUI-navigation AI agents
Official implementation for "UI-Hawk: Unleashing the Screen Stream Understanding for GUI Agents" (EMNLP 2025)
Add a description, image, and links to the gui-navigation topic page so that developers can more easily learn about it.
To associate your repository with the gui-navigation topic, visit your repo's landing page and select "manage topics."