Tools & AgentsHanzhang Zhou et al.
OpenGCUA released
OpenGCUA released — a study that leaves every component of a general-purpose computer-using agent open, combining screen control with code execution and moving the job of judging what to look at and how far the work has come from harness rules to the model
Why it matters
The authors reported that on OSWorld-v2 the average partial score of the 8 models evaluated rose by 19.6 points and that steps per task fell by 53.0% on average compared with running screen control alone. They released the implementation, prompts and evaluation logs together with an early version of a harness for real devices
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2610.22200Added in Week 43, 2026 · See that week