open source
Computer Use Gets an Open Full-Stack Baseline
OpenGCUA combines visual and programmatic interfaces, releases prompts and trajectories, and moves selected harness decisions into the model.
Summary
OpenGCUA combines visual and programmatic interfaces, releases prompts and trajectories, and moves selected harness decisions into the model.
OpenGCUA defines a generalist computer-use agent that chooses how to observe, act and organize work across GUI and code interfaces. On OSWorld-v2, the full configuration improved mean partial score by 19.6 points and reduced reported steps by 53 percent across eight tested models relative to batched GUI-only execution. The team released implementation details, prompts and trajectories plus preliminary real-device and cross-device components. Four macOS tasks also exposed large model differences in reasoning-token use; the real-device evidence remains preliminary.
Why it matters
OpenGCUA combines visual and programmatic interfaces, releases prompts and trajectories, and moves selected harness decisions into the model.
Limits and context
- On OSWorld-v2, the full configuration improved mean partial score by 19.6 points and reduced reported steps by 53 percent across eight tested models relative to batched GUI-only execution.
Key claims
OpenGCUA combines visual and programmatic interfaces, releases prompts and trajectories, and moves selected harness decisions into the model.
Qualification: On OSWorld-v2, the full configuration improved mean partial score by 19.6 points and reduced reported steps by 53 percent across eight tested models relative to batched GUI-only execution.
Evidence: source-2026-10-18-021
Sources
- arXiv preprint 2610.22200, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.