Metraipolis › archive › dc_331f26cd9561

AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents — arXiv:2608.05891

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.05891
License (as archived): CC0-1.0
Archived: 2026-10-25T21:31:18.087Z
SHA-256 of the archived text: 9b679fad933621c83733874dceee74d9ef22e50a9b097fd765db27d202b59fa3
Stable URL of this page: https://metraipolis.com/documento/dc_331f26cd9561

How to cite

AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents — arXiv:2608.05891 — arXiv (en), https://arxiv.org/abs/2608.05891 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_331f26cd9561 (Metraipolis archive dc_331f26cd9561, sha256 9b679fad933621c83733874dceee74d9ef22e50a9b097fd765db27d202b59fa3)

BibTeX

@misc{dc331f26cd9561,
  title = {AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents — arXiv:2608.05891},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05891},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_331f26cd9561; sha256 9b679fad933621c83733874dceee74d9ef22e50a9b097fd765db27d202b59fa3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05891. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.05891 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-25T21:24:38.271Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).