UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics

• URL: http://arxiv.org/abs/2604.02345v1
• Date: Wed, 11 Feb 2026 17:02:38 GMT
• Title: UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics
• Abstract summary: We propose a framework that shifts the learning focus from mimicking high-level trajectories to mastering interaction physics.<n> UI-Oceanus converts low-cost autonomous exploration into high-density generative supervision to construct a robust internal world model.
• Score: 25.60139960043983
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 superiority of our approach: models utilizing Continual Pre-Training (CPT) on synthetic dynamics outperform non-CPT baselines with an average success rate improvement of 7% on offline benchmarks, which amplifies to a 16.8% gain in real-world online navigation. Furthermore, we observe that navigation performance scales with synthetic data volume. These results confirm that grounding agents in forward predictive modeling offers a superior pathway to scalable GUI automation with robust cross-domain adaptability and compositional generalization.

Related papers

• Predicting Consequences and Reinforcing Navigation Policies with Latent World Models [31.865100130203317]
  We propose a compatibility prediction Latent World Model (LWM) for robot navigation.<n>Our key insight is that spatial proximity correlates with latent feature similarity, enabling action consequences to be evaluated directly in latent space.<n>Our approach significantly outperforms prior world model and imitation learning methods in prediction accuracy, policy learning, and real-world navigation performance.
  arXiv  Detail & Related papers  (2026-08-23T11:58:42Z)
• Scaling GUI Agents with Visual State Transitions [83.06866209578706]
  State Transition Pretraining (STP) is a new scaling axis for GUI agents.<n>STP continually pretrains a unified multimodal model on visual state transitions.<n>Our models consistently outperform baselines trained solely via direct fine-tuning across agent benchmarks.
  arXiv  Detail & Related papers  (2026-07-27T07:54:08Z)
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• Automatic Speech Recognition in the Modern Era: Architectures, Training, and Evaluation [0.0]
  Speech recognition has undergone a profound transformation over the past decade, driven by advances in deep learning.<n>This survey provides a comprehensive overview of the modern era of ASR, charting its evolution from traditional hybrid systems to the now-dominant end-to-end neural architectures.
  arXiv  Detail & Related papers  (2025-10-11T05:38:45Z)
• Orcust: Stepwise-Feedback Reinforcement Learning for GUI Agent [12.334063115362758]
  Orcust is a framework that integrates Principle-Constrained Reward Modeling and Online VM-Grounded Trajectory Construction.<n>OVTC spins up instrumented virtual machines to autonomously collect structured GUI interaction trajectories.
  arXiv  Detail & Related papers  (2025-09-22T15:40:31Z)
• From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning [59.88543114325153]
  We introduce the Seeing-to-Experiencing framework to scale the capability of navigation foundation models with reinforcement learning.<n>S2E combines the strengths of pre-training on videos and post-training through RL.<n>We establish a comprehensive end-to-end evaluation benchmark, NavBench-GS, built on photorealistic 3DGS reconstructions of real-world scenes.
  arXiv  Detail & Related papers  (2025-07-29T17:26:10Z)
• RoHOI: Robustness Benchmark for Human-Object Interaction Detection [84.78366452133514]
  Human-Object Interaction (HOI) detection is crucial for robot-human assistance, enabling context-aware support.<n>We introduce the first benchmark for HOI detection, evaluating model resilience under diverse challenges.<n>Our benchmark, RoHOI, includes 20 corruption types based on the HICO-DET and V-COCO datasets and a new robustness-focused metric.
  arXiv  Detail & Related papers  (2025-07-12T01:58:04Z)
• StyleDrive: Towards Driving-Style Aware Benchmarking of End-To-End Autonomous Driving [7.525510086747996]
  Personalization has been largely overlooked in the context of end-to-end autonomous driving (E2EAD)<n>We introduce the first large-scale real-world dataset explicitly curated for personalized E2EAD.<n>We introduce the first standardized benchmark for systematically evaluating personalized E2EAD models.
  arXiv  Detail & Related papers  (2025-06-30T15:48:38Z)
• Towards Human-Like Trajectory Prediction for Autonomous Driving: A Behavior-Centric Approach [22.81464823797471]
  HiT (Human-like Trajectory Prediction) is a novel model designed to enhance trajectory prediction by incorporating behavior-aware modules and dynamic centrality measures.<n>To evaluate HiT's performance, we conducted extensive experiments using diverse and challenging real-world datasets.
  arXiv  Detail & Related papers  (2025-05-27T05:04:01Z)
• OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis [55.390060529534644]
  We propose OS-Genesis, a novel data synthesis pipeline for Graphical User Interface (GUI) agents.<n>Instead of relying on pre-defined tasks, OS-Genesis enables agents first to perceive environments and perform step-wise interactions.<n>We demonstrate that training GUI agents with OS-Genesis significantly improves their performance on highly challenging online benchmarks.
  arXiv  Detail & Related papers  (2024-12-27T16:21:58Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.