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

*Source* · `src-wang-2024-text-world-simulators` · status: **n/a**

| field | value |
|---|---|
| kind | Preprint |
| authors | Ruoyao Wang, Graham Todd, Ziang Xiao, Xingdi Yuan, Marc-Alexandre Côté, Peter Clark, Peter Jansen |
| venue | arXiv |
| date | 2024-06-10 |
| url | https://arxiv.org/abs/2406.06485 |
| arxiv | 2406.06485 |
| accessed | 2026-10-24 |

## Notes

ByteSized32-State-Prediction: 76,369 transitions from 31 text games. GPT-4 whole-state accuracy at most 59.9%; action-driven up to 77.1%; environment-driven at most 49.7%; humans about 80% on a subset where GPT-4 averaged about 50%. Failures in arithmetic, common sense, scientific knowledge.

## Backlinks (computed)

**cited by:** [LLM explanation of simulation state](../technique/llm-explanation-of-state.md), [LLM-adjudicated state transitions (LLM as game mechanic)](../technique/llm-rule-adjudication.md)

## Citation

Ruoyao Wang, Graham Todd, Ziang Xiao, Xingdi Yuan, Marc-Alexandre Côté, Peter Clark, Peter Jansen (2024-06-10). *Can Language Models Serve as Text-Based World Simulators?*. arXiv https://arxiv.org/abs/2406.06485

---
Provenance: created in run `2026-10-24-techniques-llm-agents`.