OpenGCUA debuts an open full stack for generalist computer-use agents
The OpenGCUA project on arXiv has published its first release, aiming to open the full stack for generalist computer-use agents (GCUAs) in which the model chooses how to observe, act and organize work across visual and programmatic interfaces. The design makes code execution central and proposes harness-to-model decision transfer, moving selected observations and task-state decisions from fixed harness rules to the model. The authors report that on OSWorld-v2 their full configuration raised the mean partial score by 19.6 points across all eight evaluated models, including GPT-6 Astra and Claude Opus 5, and cut reported steps per task by an average of 53.0%; these are the authors' own results without independent replication, and they also released the implementation, prompts, evaluation trajectories and preliminary real-device harness and cross-device SDK.
The authors say frontier computer-use systems such as GPT-6 Astra's remain largely closed, limiting systematic study of their design, which is why OpenGCUA aims to open the full stack with the community.
Computer Science > Computer Vision and Pattern Recognition
arXiv:2610.22200 (cs)
[Submitted on 15 Oct 2026]
Title:OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use
Authors:Hanzhang Zhou, Long Li, Quyu Kong, Lei Wang, Panrong Tong, Long Chen, Tianyu Xia, Gongjie Zhang, Xu Zhang, Chen Liu, Jianan Zhang, Chenglin Cai, Zhengwen Zeng, Steven Hoi, Yue Wang
View a PDF of the paper titled OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use, by Hanzhang Zhou and 14 other authors
#OpenGCUA#arXiv#GPT-6 Astra#Claude Opus 5#Qwen3.8-Max#OSWorld-v2