Large Language Models as Minecraft Agents
This work addresses the challenge of AI agents in complex environments like Minecraft, but it appears incremental as it builds on existing methods without claiming major breakthroughs.
The paper tackles the problem of using Large Language Models as agents in Minecraft, evaluating them in builder and architect settings and introducing clarification questions to address challenges, with results compared against previous works.
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.