World Models for Digital Agents: An Agent-Centric Survey
Preprint
- 5 November 2026
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Digital agents operating in software-defined environments, including games, web interfaces, mobile GUIs, tool-use systems, and code repositories, often benefit from anticipating the consequences of actions before execution. World models provide a principled mechanism for such anticipation, but their utility in digital settings is neither automatic nor uniform. Unlike physical environments, digital transitions are interface-mediated and program-governed, and the value of prediction depends less on perceptual realism than on preserving functionally relevant consequences for downstream decisions. This survey presents the first dedicated agent-centric treatment of world models across major digital-agent domains. We introduce a unified design space, W = (X , L, U), organized around three complementary questions: what is modeled, how predictive capability is built, and how world models are used inside the agent loop. Through this lens, we synthesize a rapidly growing literature spanning semantic transition models, visual and latent simulators, tool-state predictors, executable code-based world models, and hybrid predictive systems. We further examine environments, datasets, and evaluation protocols as a coupled empirical pipeline, and highlight open challenges, notably the persistent gap between predictive fidelity and downstream utility.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Understanding World or Predicting Future? A Comprehensive Survey of World ModelsACM Computing Surveys, 2025
- Mastering diverse control tasks through world modelsNature, 2025
- A survey on large language model based autonomous agentsFrontiers of Computer Science, 2024
- Competition-level code generation with AlphaCodeScience, 2022
- Mastering Atari, Go, chess and shogi by planning with a learned modelNature, 2020
- Grandmaster level in StarCraft II using multi-agent reinforcement learningNature, 2019
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- Human-level control through deep reinforcement learningNature, 2015
- The Arcade Learning Environment: An Evaluation Platform for General AgentsJournal of Artificial Intelligence Research, 2013
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004