Saved in:
Bibliographic Details
Main Authors: Li, Shufan, Kallidromitis, Konstantinos, Gokul, Akash, Kato, Yusuke, Kozuka, Kazuki, Grover, Aditya
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.14014
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912767612551168
author Li, Shufan
Kallidromitis, Konstantinos
Gokul, Akash
Kato, Yusuke
Kozuka, Kazuki
Grover, Aditya
author_facet Li, Shufan
Kallidromitis, Konstantinos
Gokul, Akash
Kato, Yusuke
Kozuka, Kazuki
Grover, Aditya
contents World models have shown great utility in improving the task performance of embodied agents. While prior work largely focuses on pixel-space world models, these approaches face practical limitations in GUI settings, where predicting complex visual elements in future states is often difficult. In this work, we explore an alternative formulation of world modeling for GUI agents, where state transitions are described in natural language rather than predicting raw pixels. First, we introduce MobileWorldBench, a benchmark that evaluates the ability of vision-language models (VLMs) to function as world models for mobile GUI agents. Second, we release MobileWorld, a large-scale dataset consisting of 1.4M samples, that significantly improves the world modeling capabilities of VLMs. Finally, we propose a novel framework that integrates VLM world models into the planning framework of mobile agents, demonstrating that semantic world models can directly benefit mobile agents by improving task success rates. The code and dataset is available at https://github.com/jacklishufan/MobileWorld
format Preprint
id arxiv_https___arxiv_org_abs_2512_14014
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MobileWorldBench: Towards Semantic World Modeling For Mobile Agents
Li, Shufan
Kallidromitis, Konstantinos
Gokul, Akash
Kato, Yusuke
Kozuka, Kazuki
Grover, Aditya
Artificial Intelligence
World models have shown great utility in improving the task performance of embodied agents. While prior work largely focuses on pixel-space world models, these approaches face practical limitations in GUI settings, where predicting complex visual elements in future states is often difficult. In this work, we explore an alternative formulation of world modeling for GUI agents, where state transitions are described in natural language rather than predicting raw pixels. First, we introduce MobileWorldBench, a benchmark that evaluates the ability of vision-language models (VLMs) to function as world models for mobile GUI agents. Second, we release MobileWorld, a large-scale dataset consisting of 1.4M samples, that significantly improves the world modeling capabilities of VLMs. Finally, we propose a novel framework that integrates VLM world models into the planning framework of mobile agents, demonstrating that semantic world models can directly benefit mobile agents by improving task success rates. The code and dataset is available at https://github.com/jacklishufan/MobileWorld
title MobileWorldBench: Towards Semantic World Modeling For Mobile Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2512.14014