[2604.02345] UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics

Computer Science > Machine Learning arXiv:2604.02345 (cs) [Submitted on 11 Feb 2026] Title:UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics Authors:Mengzhou Wu, Yuzhe Guo, Yuan Cao, Haochuan Lu, Songhe Zhu, Pingzhe Qu, Xin Chen, Kang Qin, Zhongpu Wang, Xiaode Zhang, Xinyi Wang, Wei Dai, Gang Cao, Yuetang Deng, Zhi Gong, Dezhi Ran, Linyi Li, Wei Yang, Tao Xie View a PDF of the paper titled UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics, by Mengzhou Wu and 18 other authors View PDF HTML (experimental) Abstract:Scaling generalist GUI agents is hindered by the data scalability bottleneck of expensive human demonstrations and the "distillation ceiling" of synthetic teacher supervision. To transcend these limitations, we propose UI-Oceanus, a framework that shifts the learning focus from mimicking high-level trajectories to mastering interaction physics via ground-truth environmental feedback. Through a systematic investigation of self-supervised objectives, we identify that forward dynamics, defined as the generative prediction of future interface states, acts as the primary driver for scalability and significantly outweighs inverse inference. UI-Oceanus leverages this insight by converting low-cost autonomous exploration, which is verified directly by system execution, into high-density generative supervision to construct a robust internal world model. Experimental evaluations across a series of models demonstrate the decisive superior...