@inproceedings{li-etal-2026-mobileworldbench,
title = "{M}obile{W}orld{B}ench: Towards Semantic World Modeling For Mobile Agents",
author = "Li, Shufan and
Kallidromitis, Konstantinos and
Gokul, Akash and
Kato, Yusuke and
Kozuka, Kazuki and
Grover, Aditya",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2401/",
pages = "54571--54592",
ISBN = "979-8-89176-459-0",
abstract = "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 mobile agent settings, where predicting complex visual GUI elements in future states is often difficult. In this work, we explore an alternative formulation of world modeling for mobile agents, where state transitions are described in natural language rather than predicting screenshot pixels. First, we introduce MobileWorldBench, a benchmark that evaluates the ability of vision-language models (VLMs) to function as world models for mobile agents. Second, we release MobileWorld, a large-scale dataset consisting of 1.4M samples, that 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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-mobileworldbench">
<titleInfo>
<title>MobileWorldBench: Towards Semantic World Modeling For Mobile Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shufan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantinos</namePart>
<namePart type="family">Kallidromitis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akash</namePart>
<namePart type="family">Gokul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Kato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazuki</namePart>
<namePart type="family">Kozuka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Grover</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>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 mobile agent settings, where predicting complex visual GUI elements in future states is often difficult. In this work, we explore an alternative formulation of world modeling for mobile agents, where state transitions are described in natural language rather than predicting screenshot pixels. First, we introduce MobileWorldBench, a benchmark that evaluates the ability of vision-language models (VLMs) to function as world models for mobile agents. Second, we release MobileWorld, a large-scale dataset consisting of 1.4M samples, that 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.</abstract>
<identifier type="citekey">li-etal-2026-mobileworldbench</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2401/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>54571</start>
<end>54592</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MobileWorldBench: Towards Semantic World Modeling For Mobile Agents
%A Li, Shufan
%A Kallidromitis, Konstantinos
%A Gokul, Akash
%A Kato, Yusuke
%A Kozuka, Kazuki
%A Grover, Aditya
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F li-etal-2026-mobileworldbench
%X 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 mobile agent settings, where predicting complex visual GUI elements in future states is often difficult. In this work, we explore an alternative formulation of world modeling for mobile agents, where state transitions are described in natural language rather than predicting screenshot pixels. First, we introduce MobileWorldBench, a benchmark that evaluates the ability of vision-language models (VLMs) to function as world models for mobile agents. Second, we release MobileWorld, a large-scale dataset consisting of 1.4M samples, that 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.
%U https://aclanthology.org/2026.emnlp-main.2401/
%P 54571-54592
Markdown (Informal)
[MobileWorldBench: Towards Semantic World Modeling For Mobile Agents](https://aclanthology.org/2026.emnlp-main.2401/) (Li et al., EMNLP 2026)
ACL
- Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozuka, and Aditya Grover. 2026. MobileWorldBench: Towards Semantic World Modeling For Mobile Agents. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 54571–54592, Budapest, Hungary. Association for Computational Linguistics.