# Can Language Models Serve as Text-Based World Simulators?

arXiv: https://arxiv.org/abs/2406.06485 · HTML: https://mlsanity.com/paper/2406.06485/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 21 references that are in the map.
- First posted on arXiv 10 Jun 2024.

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [Interactive Fiction Games: A Colossal Adventure](https://mlsanity.com/paper/1909.05398/) (2019)
- [Learning to Speak and Act in a Fantasy Text Adventure Game](https://mlsanity.com/paper/1903.03094/) (2019)
- [From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought](https://mlsanity.com/paper/2306.12672/) (2023)
- [WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment](https://mlsanity.com/paper/2402.12275/) (2024)
- [Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling](https://mlsanity.com/paper/2301.12050/) (2023)
- [Graph Constrained Reinforcement Learning for Natural Language Action Spaces](https://mlsanity.com/paper/2001.08837/) (2020)
- [Learning Dynamic Belief Graphs to Generalize on Text-Based Games](https://mlsanity.com/paper/2002.09127/) (2020)
- [ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games](https://mlsanity.com/paper/2305.14879/) (2023)
- [A Systematic Survey of Text Worlds as Embodied Natural Language Environments](https://mlsanity.com/paper/2107.04132/) (2021)
- [Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions](https://mlsanity.com/paper/2304.03816/) (2023)
- [Generating Interactive Worlds with Text](https://mlsanity.com/paper/1911.09194/) (2019)

## Built on by (most cited first, 30 of 52)

- [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024)
- [Vid2World: Crafting Video Diffusion Models to Interactive World Models](https://mlsanity.com/paper/2505.14357/) (2025)
- [Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning](https://mlsanity.com/paper/2602.10090/) (2026)
- [Knowledge Mechanisms in Large Language Models: A Survey and Perspective](https://mlsanity.com/paper/2407.15017/) (2024)
- [From Word to World: Can Large Language Models be Implicit Text-based World Models?](https://mlsanity.com/paper/2512.18832/) (2025)
- [RLVR-World: Training World Models with Reinforcement Learning](https://mlsanity.com/paper/2505.13934/) (2025)
- [Planning with Reasoning using Vision Language World Model](https://mlsanity.com/paper/2509.02722/) (2025)
- [Qwen-AgentWorld: Language World Models for General Agents](https://mlsanity.com/paper/2606.24597/) (2026)
- [CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks](https://mlsanity.com/paper/2406.13945/) (2024)
- [Text2World: Benchmarking Large Language Models for Symbolic World Model Generation](https://mlsanity.com/paper/2502.13092/) (2025)
- [Making Large Language Models into World Models with Precondition and Effect Knowledge](https://mlsanity.com/paper/2409.12278/) (2024)
- [Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models](https://mlsanity.com/paper/2601.19834/) (2026)
- [Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches](https://mlsanity.com/paper/2501.03151/) (2025)
- [Generative Emergent Communication: Large Language Model is a Collective World Model](https://mlsanity.com/paper/2501.00226/) (2024)
- [Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents](https://mlsanity.com/paper/2506.00320/) (2025)
- [EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL](https://mlsanity.com/paper/2605.18703/) (2026)
- [R-WoM: Retrieval-augmented World Model For Computer-use Agents](https://mlsanity.com/paper/2510.11892/) (2025)
- [Evolution and The Knightian Blindspot of Machine Learning](https://mlsanity.com/paper/2501.13075/) (2025)
- [Revisiting the Othello World Model Hypothesis](https://mlsanity.com/paper/2503.04421/) (2025)
- [LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed](https://mlsanity.com/paper/2411.08794/) (2024)
- [Enhancing Agent Learning through World Dynamics Modeling](https://mlsanity.com/paper/2407.17695/) (2024)
- [Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents](https://mlsanity.com/paper/2602.16246/) (2026)
- [Towards Building Specialized Generalist AI with System 1 and System 2 Fusion](https://mlsanity.com/paper/2407.08642/) (2024)
- [G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration](https://mlsanity.com/paper/2506.09272/) (2025)
- [Evolution of Cooperation in LLM-Agent Societies: A Preliminary Study Using Different Punishment Strategies](https://mlsanity.com/paper/2504.19487/) (2025)
- [Beyond State Consistency: Behavior Consistency in Text-Based World Models](https://mlsanity.com/paper/2604.13824/) (2026)
- [Bridging the Agent-World Gap: Text World Models for LLM-based Agents](https://mlsanity.com/paper/2606.09032/) (2026)
- [Trajectory World Models for Heterogeneous Environments](https://mlsanity.com/paper/2502.01366/) (2025)
- [From Pixels to States: Rethinking Interactive World Models as Game Engines](https://mlsanity.com/paper/2607.14076/) (2026)
- [C-World: A Computer Use Agent Environment Creator](https://mlsanity.com/paper/2601.06328/) (2026)

## Abstract (arXiv)

Virtual environments play a key role in benchmarking advances in complex planning and decision-making tasks but are expensive and complicated to build by hand. Can current language models themselves serve as world simulators, correctly predicting how actions change different world states, thus bypassing the need for extensive manual coding? Our goal is to answer this question in the context of text-based simulators. Our approach is to build and use a new benchmark, called ByteSized32-State-Prediction, containing a dataset of text game state transitions and accompanying game tasks. We use this to directly quantify, for the first time, how well LLMs can serve as text-based world simulators. We test GPT-4 on this dataset and find that, despite its impressive performance, it is still an unreliable world simulator without further innovations. This work thus contributes both new insights into current LLM's capabilities and weaknesses, as well as a novel benchmark to track future progress as new models appear.