Large Language Models as Minecraft Agents

Madge, Chris, Poesio, Massimo

arXiv.org Artificial Intelligence 

In this work we examine the use of Large Language Models (LLMs) in the challenging setting of acting as a Minecraft agent. We apply and evaluate LLMs in the builder and architect settings, introduce clarification questions and examining the challenges and opportunities for improvement. In addition, we present a platform for online interaction with the agents and an evaluation against previous works.