Microsoft open-sources 4B agent that picks GUI clicks or bash each turn, scoring 66% on OSWorld
AIFlow_ML · x · 2026-10-31
Microsoft's Mage team released Mage-VL-Cowork on Hugging Face under Apache-2.0: a 4B multimodal policy holding two action channels in one model — computeruse for mouse/keyboard and bash for a persistent shell — with no external router; the model picks the channel each turn. Its model card reports 66% on OSWorld-Verified, edging out Muse Glimmer 30B (65.9%) and Qwen3.6-27B (63.9%), near GPT-5.4-mini (69.6%). The author warns the bash channel means you should sandbox it first.
Related event: Microsoft Open-Sources Mage-VL-Cowork, a 4B Computer-Use Agent(9 posts)→
More from coding & agent
- Dev shares safety architecture for self-improving agent: out-of-band release controller with passkey approvals — viksit · 2026-11-01
- Dev shares Grok Bot team-building guide: few focused bots that write their own skills — CurieuxExplorer · 2026-11-01
- 747 AI-agent ideas reveal a scaling law for idea descent: +17% per doubling — DimitrisPapail · 2026-11-01
- Magnific Move + Claude Opus: Halloween game animated in one chat — petewoodbridge · 2026-11-01
- AI-Driven Frame Rate Optimization Cuts Render Time by 9%-15% Across Six Scenes — AIandDesign · 2026-11-01
- Parcha founder: You may not need an agent after all — decision models vs workflows — blaizedsouza · 2026-11-01