Tencent HY Frontier Multimodal Agent Team has released UI-Mate-9B, an open-weight foundation GUI agent designed for long-horizon tasks across applications and operating systems. The model observes live screenshots to reason over visible states and produces structured keyboard and mouse actions for native desktop interaction.
- Base model: Qwen3.5-9B with 9 billion parameters.
- Supports general computer use from natural-language instructions and demonstration-guided use that adapts reusable workflows.
- Trained via supervised fine-tuning followed by online reinforcement learning in executable GUI environments.
- Licensed under Apache-2.0.
The release enables research into screenshot-based GUI agents with one-shot procedural learning capabilities.