Microsoft Open-Sources 4B Agent Choosing Clicks or Bash Each Turn, Scores 66% on OSWorld
AIFlow_ML · x · 2026-10-31
Microsoft open-sourced a 4B agent model that decides each turn whether to use mouse clicks or bash commands, with no router, scoring 66% on OSWorld-Verified per its model card. The poster adds a security caveat: bash access means it should only ever run inside a throwaway sandbox.
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