# AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents arXiv: https://arxiv.org/abs/2608.05891 ยท HTML: https://mlsanity.com/paper/2608.05891/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in World model security and GUI agents, one of 11 directions in World models. - Builds on 33 of its 47 references that are in the map. - First posted on arXiv 6 Aug 2026. ## Placed in - World models / [World model security and GUI agents](https://mlsanity.com/wm/world-model-security-and-gui-agents/) - LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/) ## Builds on (most cited first, 30 of 33) - [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025) - [TTRL: Test-Time Reinforcement Learning](https://mlsanity.com/paper/2504.16084/) (2025) - [UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2509.02544/) (2025) - [Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents](https://mlsanity.com/paper/2411.06559/) (2024) - [Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks](https://mlsanity.com/paper/2501.11733/) (2025) - [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024) - [UI-Venus Technical Report: Building High-performance UI Agents with RFT](https://mlsanity.com/paper/2508.10833/) (2025) - [AppAgent v2: Advanced Agent for Flexible Mobile Interactions](https://mlsanity.com/paper/2408.11824/) (2024) - [Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence](https://mlsanity.com/paper/2604.18292/) (2026) - [MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment](https://mlsanity.com/paper/2507.05720/) (2025) - [From Word to World: Can Large Language Models be Implicit Text-based World Models?](https://mlsanity.com/paper/2512.18832/) (2025) - [ViMo: A Generative Visual GUI World Model for App Agents](https://mlsanity.com/paper/2504.13936/) (2025) - [Code2World: A GUI World Model via Renderable Code Generation](https://mlsanity.com/paper/2602.09856/) (2026) - [Qwen-AgentWorld: Language World Models for General Agents](https://mlsanity.com/paper/2606.24597/) (2026) - [WebWorld: A Large-Scale World Model for Web Agent Training](https://mlsanity.com/paper/2602.14721/) (2026) - [MobileDreamer: Generative Sketch World Model for GUI Agent](https://mlsanity.com/paper/2601.04035/) (2026) - [Falcon-UI: Understanding GUI Before Following User Instructions](https://mlsanity.com/paper/2412.09362/) (2024) - [MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning](https://mlsanity.com/paper/2508.03700/) (2025) - [MobileWorldBench: Towards Semantic World Modeling For Mobile Agents](https://mlsanity.com/paper/2512.14014/) (2025) - [Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile Agents](https://mlsanity.com/paper/2505.11891/) (2025) - [Computer-Using World Model](https://mlsanity.com/paper/2602.17365/) (2026) - [GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL](https://mlsanity.com/paper/2602.22190/) (2026) - [OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution](https://mlsanity.com/paper/2601.20380/) (2026) - [Generative Visual Code Mobile World Models](https://mlsanity.com/paper/2602.01576/) (2026) - [MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research](https://mlsanity.com/paper/2605.26114/) (2026) - [STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization](https://mlsanity.com/paper/2511.13091/) (2025) - [OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis](https://mlsanity.com/paper/2604.15093/) (2026) - [MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning](https://mlsanity.com/paper/2505.12299/) (2025) - [How Mobile World Model Guides GUI Agents?](https://mlsanity.com/paper/2605.10347/) (2026) - [CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning](https://mlsanity.com/paper/2602.24142/) (2026) ## Built on by (most cited first, 2 of 2) - [The GUI Is Not the State: Diagnosing State Aliasing in GUI World Models](https://mlsanity.com/paper/2609.32679/) (2026) - [Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents](https://mlsanity.com/paper/2610.11942/) (2026) ## Abstract (arXiv) Mobile GUI agents can operate apps through pixel perception and touch actions, making them a promising interface for collecting and improving long-horizon mobile interaction policies. However, real trajectories are difficult to obtain for sensitive apps and privacy-critical operations. At the same time, existing simulated environments are costly to scale up, and GUI world models still suffer from unstable generation, limited modality coverage, and inconsistent action-transition logic. To address these limitations, we propose AppDeltaWorld, a transition-grounded delta code world model that predicts the next GUI as a reachable code update rather than as an unconstrained image or text description. AppDeltaWorld retrieves app-specific Level-1 HTML references under an action-transition constraint, generates Level-2 executable HTML conditioned on the current screen, action, predicted next-screen text, and retrieved structure, and inserts generated visual assets into image slots before browser rendering. As a world model, AppDeltaWorld achieves the highest fidelity on CMGUIBench-500 under Code2World evaluation, with clear gains in structural layout and UI element reconstruction over image-only and code-only baselines. As a training environment, AppDeltaWorld supports filtered closed-loop SFT data construction that, when combined with public supervision, enables AppDeltaAgent to achieve state-of-the-art performance on AndroidLens and consistent gains on MobileGym and MobileWorld. Moreover, world-model-based test-time reinforcement learning enables policy adaptation and shows further improvements without additional interaction with real apps.