AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents
Ranking
Overall
64
Content
75
Popularity
39
Observed public metrics from 1 member.
Merged summary
TL;DR - AppDeltaWorld is a GUI world model that predicts the next mobile screen as a constrained, executable HTML "delta code update" rather than a raw image or free-text description, giving agents a scalable synthetic environment when real app trajectories are unavailable due to privacy or cost.
- Two-level pipeline: retrieves app-specific Level-1 HTML references under an action-transition constraint, then generates Level-2 executable HTML conditioned on current screen, action, predicted next-screen text, and retrieved structure; generated visual assets are inserted into image slots before browser rendering.
- As a world model, it reports the highest fidelity on CMGUIBench-500 under Code2World evaluation, with gains in structural layout and UI element reconstruction over image-only and code-only baselines.
- As a training environment, it supports filtered closed-loop SFT data construction; combined with public supervision, AppDeltaAgent reaches state-of-the-art on AndroidLens and consistent gains on MobileGym and MobileWorld.
- World-model-based test-time reinforcement learning further improves policy adaptation without any additional interaction with real apps.
Sources (1)
AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - AppDeltaWorld is a GUI world model that predicts the next mobile screen as a constrained, executable HTML "delta code update" rather than a raw image or free-text description, giving agents a scalable synthetic environment when real app trajectories are unavailable due to privacy or cost.
- Two-level pipeline: retrieves app-specific Level-1 HTML references under an action-transition constraint, then generates Level-2 executable HTML conditioned on current screen, action, predicted next-screen text, and retrieved structure; generated visual assets are inserted into image slots before browser rendering.
- As a world model, it reports the highest fidelity on CMGUIBench-500 under Code2World evaluation, with gains in structural layout and UI element reconstruction over image-only and code-only baselines.
- As a training environment, it supports filtered closed-loop SFT data construction; combined with public supervision, AppDeltaAgent reaches state-of-the-art on AndroidLens and consistent gains on MobileGym and MobileWorld.
- World-model-based test-time reinforcement learning further improves policy adaptation without any additional interaction with real apps.