The use of generative AI in video game development is on the rise, and as the conversational and other capabilities of large language models continue to improve, we expect LLM-driven non-player characters (NPCs) to become widely deployed. In this paper, we seek to understand how human players collaborate with LLM-driven NPCs to accomplish in-game goals. We design a minigame within Minecraft where a player works with two GPT4-driven NPCs to complete a quest. We perform a user study in which 28 Minecraft players play this minigame and share their feedback. On analyzing the game logs and recordings, we find that several patterns of collaborative behavior emerge from the NPCs and the human players. We also report on the current limitations of language-only models that do not have rich game-state or visual understanding. We believe that this preliminary study and analysis will inform future game developers on how to better exploit these rapidly improving generative AI models for collaborative roles in games.

Technology these days is amazing. Thanks to tech giants like Google, Artificial Intelligence (AI) is present on plenty of phones and in plenty of homes. AI is able to perform tasks that require human levels of intelligence by'learning' patterns and predicting outcomes. So, let's be honest – it was only a matter of time before we tried to figure out how to get machines to play D&D. There have been plenty of attempts to make AI RPGs happen in the past.