Qwen Releases Qwen-CUA: A Native Computer-Use Agent
xhluca · x · 2026-08-03
The Qwen team introduced Qwen-CUA, a native computer-use agent designed to unlock interactions with graphical user interfaces (GUIs).
The agent features three core capabilities:
- Native Perception: Relies solely on screenshots for visual understanding, without needing DOM trees or accessibility trees.
- Native Interaction: Simulates mouse and keyboard events across browsers, desktop apps, and professional software without task-specific APIs.
- Native Intelligence: Maintains long-horizon visual context, verifies progress, and learns from large-scale interactive experiences with verifiable outcomes.
To enable large-scale training, the team built an infrastructure with approximately 40K verifiable tasks and nearly 100K vCPUs to support tens of thousands of concurrent environments.
More from coding & agent
- Blender + ComfyUI + LTX-LoRA Workflow: Low-Cost AI Cinematic Rendering — waterarttrkgl · 2026-08-03
- Dev Test: Using AI for PCB Design Lowers the Learning Curve — pramodk73 · 2026-08-03
- Dev Tests: LLMs Have Almost Solved Feature Engineering for Tabular Data — mariofilhoml · 2026-08-03
- Claude Code Finds COLDCARD Wallet Vulnerability in 8 Minutes — rickasaurus · 2026-08-03
- Vibe coding can't conquer enterprise ERP? Practitioner reveals integration challenges — MatthewChang · 2026-08-03
- Inside Uber Eats' Self-Tuning Multi-Agent System for Photo Processing — prashantkr_00 · 2026-08-03