Word2Minecraft: Generating 3D Game Levels through Large Language Models

We present Word2Minecraft, a system that leverages large language models to generate playable game levels in Minecraft based on structured stories. The system transforms narrative elements-such as protagonist goals, antagonist challenges, and environmental settings-into game levels with both spatial and gameplay constraints. We introduce a flexible framework that allows for the customization of story complexity, enabling dynamic level generation. The system employs a scaling algorithm to maintain spatial consistency while adapting key game elements. We evaluate Word2Minecraft using both metric-based and human-based methods. Our results show that GPT-4-Turbo outperforms GPT-4o-Mini in most areas, including story coherence and objective enjoyment, while the latter excels in aesthetic appeal. We also demonstrate the system' s ability to generate levels with high map enjoyment, offering a promising step forward in the intersection of story generation and game design. We open-source the code atthis https URL

@article{huang2025_2503.16536,
  title={ Word2Minecraft: Generating 3D Game Levels through Large Language Models },
  author={ Shuo Huang and Muhammad Umair Nasir and Steven James and Julian Togelius },
  journal={arXiv preprint arXiv:2503.16536},
  year={ 2025 }
}