Summary of Game Generation Via Large Language Models, by Chengpeng Hu et al.
Game Generation via Large Language Models
by Chengpeng Hu, Yunlong Zhao, Jialin Liu
First submitted to arxiv on: 11 Apr 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Recently, large language models (LLMs) have revolutionized procedural content generation by enabling the creation of game rules and levels simultaneously. While previous attempts focused on generating levels for specific games with defined rules, such as Super Mario Bros. and Zelda, this paper proposes a novel LLM-based framework that can generate both game rules and levels from scratch. By leveraging video game description language, the framework can create new game scenarios and levels using prompts that consider different combinations of context. The paper’s findings expand the current applications of LLMs and provide new insights for generating new games in procedural content generation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper explores how large language models (LLMs) can be used to generate new video games. Right now, these models are mainly used to create levels for specific games like Super Mario Bros. or Zelda. The authors of this paper want to go beyond that and create entire games from scratch using LLMs. They propose a special way of writing code that combines language description with game rules and level design. By testing their approach with different prompts, they show that it’s possible to generate new game scenarios and levels. This research has the potential to open up new possibilities for creating games in the future. |
