# ViMo: A Generative Visual GUI World Model for App Agents

Authors: Dezhao Luo, Bohan Tang, Kang Li, Georgios Papoudakis, Jifei Song, Shaogang Gong, Jianye Hao, Jun Wang, Kun Shao.

Predicts future mobile-app screens to help agents compare possible actions, separating graphic content from textual content.

First public: 2025-04-15.
ArXiv initial submission: 2025-04-15.

[Original paper](https://arxiv.org/abs/2504.13936) · [Reading-list entry](https://neural-os.com/reading-list/papers/2504.13936/)
[Preprint BibTeX](https://neural-os.com/reading-list/papers/2504.13936/citation.bib) · [Preprint CSL-JSON](https://neural-os.com/reading-list/papers/2504.13936/citation.csl.json) · [JSON record](https://neural-os.com/reading-list/papers/2504.13936/record.json)

**Contribution:** Uses symbolic text placeholders to preserve layout while assigning graphical and text prediction to separate components.

**Model output:** Future mobile GUI images assembled from graphics and text predictions.

**Action interface:** Candidate mobile-app actions.

**State and memory:** Screen-and-action-conditioned prediction; symbolic text representation retains text locations and layout.

**Relationship to NeuralOS:** Visual GUI world-model research released in April 2025, before NeuralOS's July 2025 preprint.

**Scope and limitations:** The experiments predict mobile-app screens for agent planning.

[Relationship source](https://arxiv.org/abs/2504.13936)

Related terms: ViMo, GUI world model, next-screen prediction, mobile app simulation.

## Approaches

- [GUI prediction and planning](https://neural-os.com/reading-list/guides/games-to-computers/#gui-prediction-and-planning): Predict the consequences of interface actions so an agent can compare alternatives before execution. Prediction targets include textual changes, screen images, and renderable interface code.

Reading-list version 1.0.1; literature checked through 2026-10-19.