Summary of A Survey on Large Language Model-based Game Agents, by Sihao Hu et al.
A Survey on Large Language Model-Based Game Agents
by Sihao Hu, Tiansheng Huang, Fatih Ilhan, Selim Tekin, Gaowen Liu, Ramana Kompella, Ling Liu
First submitted to arxiv on: 2 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 This paper provides a comprehensive overview of Large Language Model (LLM)-based game agents, which aim to advance Artificial General Intelligence (AGI) by empowering game agents with human-like decision-making capabilities. The study introduces the conceptual architecture of LLM-based game agents, comprising six functional components: perception, memory, thinking, role-playing, action, and learning. The authors survey existing representative LLM-based game agents documented in the literature, showcasing methodologies and adaptation agility across various genres of games, including adventure, communication, competition, cooperation, simulation, and crafting & exploration games. The paper concludes by outlining future research directions in this emerging field. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study explores how to make computer game characters smarter and more human-like. It looks at a type of artificial intelligence called Large Language Models (LLMs) that can learn from playing games. The researchers describe the basic structure of LLM-based game agents, which have six main parts: seeing, remembering, thinking, pretending, taking action, and learning. They also review existing examples of LLM-based game agents and how they perform in different types of games. Finally, the study suggests areas where more research is needed to make these game agents even better. |
Keywords
» Artificial intelligence » Large language model
