← all releases
Alibaba·Dec 30, 2025·Not specified·open source

MAI-UI

MAI-UI is a family of multimodal GUI agents developed by Alibaba Tongyi Lab, designed to integrate tool use, agent user interaction, device–cloud collaboration, and online reinforcement learning. These agents have achieved state-of-the-art results in general GUI grounding and mobile GUI navigation, surpassing models like Gemini-2.5-Pro, Seed1.8, and UI-Tars-2 on AndroidWorld.

AI AgentsAgentic AILLMs
visit website
overview

MAI-UI is a family of multimodal GUI agents developed by Alibaba Tongyi Lab, designed to integrate tool use, agent user interaction, device–cloud collaboration, and online reinforcement learning. These agents have achieved state-of-the-art results in general GUI grounding and mobile GUI navigation, surpassing models like Gemini-2.5-Pro, Seed1.8, and UI-Tars-2 on AndroidWorld.

key features
  • 01Integration of tool use and agent user interaction
  • 02Device–cloud collaboration architecture
  • 03Online reinforcement learning for improved performance
  • 04High accuracy in GUI grounding tasks
  • 05Superior mobile GUI navigation capabilities
related productsbrowse all →
llmockopen sourcellmock is a deterministic mock LLM server designed for testing purposes. It provides a real HTTP server with authentic SSE streams, allowing developers to simulate interactions with various LLM APIs like OpenAI, Claude, and Gemini without incurring costs or dealing with non-deterministic results.AIBuildAIopen sourceAIBuildAI is an AI agent that autonomously constructs AI models. Given a specific task, it initiates an agent loop to analyze the problem, design models, and execute training processes, all without human intervention.MiroThinkeropen sourceMiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.