Summary of Collaborative Quest Completion with Llm-driven Non-player Characters in Minecraft, by Sudha Rao et al.
Collaborative Quest Completion with LLM-driven Non-Player Characters in Minecraft
by Sudha Rao, Weijia Xu, Michael Xu, Jorge Leandro, Ken Lobb, Gabriel DesGarennes, Chris Brockett, Bill Dolan
First submitted to arxiv on: 3 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 The paper explores human-player collaboration with large language model-driven non-player characters (LLM-NPCs) in video games, focusing on a Minecraft minigame where players work with two GPT4-driven NPCs to complete quests. The study analyzes game logs and recordings from 28 participants, revealing patterns of collaborative behavior between the NPCs and human players. The findings highlight limitations of language-only models lacking rich game-state or visual understanding, offering insights for future game developers on leveraging generative AI for collaborative roles. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at how people work with computer characters in video games. It’s like a puzzle game where you need to work together with two special computer friends (NPCs) to get the job done. They used a popular game called Minecraft and had 28 players try it out. The results show that there are certain ways people and these NPCs work together, but they also found some limits of how good these computers can be at understanding what’s going on in the game. |
Keywords
» Artificial intelligence » Large language model
