Word2Minecraft: Generating 3D Game Levels through Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Shuo, Nasir, Muhammad Umair, James, Steven, Togelius, Julian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908276249067520
author Huang, Shuo
Nasir, Muhammad Umair
James, Steven
Togelius, Julian
author_facet Huang, Shuo
Nasir, Muhammad Umair
James, Steven
Togelius, Julian
contents 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 at https://github.com/JMZ-kk/Word2Minecraft/tree/word2mc_v0
format Preprint
id arxiv_https___arxiv_org_abs_2503_16536
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Word2Minecraft: Generating 3D Game Levels through Large Language Models
Huang, Shuo
Nasir, Muhammad Umair
James, Steven
Togelius, Julian
Computation and Language
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 at https://github.com/JMZ-kk/Word2Minecraft/tree/word2mc_v0
title Word2Minecraft: Generating 3D Game Levels through Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2503.16536