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
- ERP•AI launches headless SaaS with $0 seats that bills machines: $1 buys 4,000 record writes — rohanpaul_ai · 2026-10-16
- FDE-Gym benchmark shows huge gap on real AI delivery tasks: top model scores 0.563 — DeepLethe · 2026-10-16
- Vibe-coded dashboard leaked franchise financials before anyone logged in — shauntrennery · 2026-10-16
- Fintech HR built a sourcing agent on 60,000 past applicants — 30 qualified candidates in a month — G0NZ0BOY · 2026-10-16
- Orchestrating a 100-image portrait of humanity for aliens with ChatGPT, Argon and p5.brush — dx8xb · 2026-10-16
- 3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W — Teknium · 2026-10-16