Morning Brief · November 3rd 2026

An open 27-billion-parameter computer-use agent scores 80.2 on OSWorld-Verified

CUA-Master-27B, from a team led by Xinlei Yu, scores 80.2 on , a of operating a real desktop, plus 36.9 on OSWorld 2.0 and 25.0 on Agents' Last Exam. Its training data comes from workflows mined from instructional videos, rebuilt into tasks, with a retry mechanism that rolls a real environment back to a snapshot after a failure. A model of that size is small enough to run privately. The scores are the authors' own. SourcesA

Sources

ACUA-Master: scaling computer-use agents through open-world recursive improvements (arXiv 2611.03126, via Hugging Face)huggingface.co

This story ran in the Morning Brief of November 3rd 2026.

Meta cleared AI videos of coaches touching young athletes until a reporter called

Yandex publishes attention kernels that train faster on Nvidia's Blackwell chips