New Training Recipe Teaches Agents to Mix GUI, Code and Terminal Use

A paper introduces Mage-VL-Cowork, a full training recipe for computer-use agents that learn hybrid policies combining visual GUI interaction with code and terminal execution, using evolved harnesses.

Read the full story at arXiv cs.CL ↗

Timeline · 1 report

2026-11-02 05:00 · arXiv cs.CL
Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses

More stories

Microsoft releases Mage-VL-Cowork, a 4B open-weights computer-use vision-language model — Hugging Face model releases
DeepSeek open-sources dsh-superagent, a router-worker coding agent prototype — Bloomberg AI
OpenAI plans post-midterms push for AI 'speed limits' and 'compute campus' rebrand — Tom's Guide AI
OpenAI signs UAE deals with ADNOC and G42 to deploy frontier AI across energy sector — Reuters AI
HSBC to open Hong Kong AI institute following Singapore launch — Reuters AI
SemiAnalysis launches GDPx benchmark measuring agentic capabilities across 11 domains — Techmeme
AI startups Midstream Health, Casap, and Bites raise $116M across new funding rounds — Techmeme
South Korea's Lee vows bold AI investment in record budget push — Economic Times Tech

Get the daily brief of stories like this at 6:30 every morning →