Player-Driven Emergence in LLM-Driven Game Narrative

arXiv:2404.17027v1 Announce Type: new
Abstract: We explore how interaction with large language models (LLMs) can give rise to emergent behaviors, empowering players to participate in the evolution of game narratives. Our testbed is a text-adventure game in which players attempt to solve a mystery under a fixed narrative premise, but can freely interact with non-player characters generated by GPT-4, a large language model. We recruit 28 gamers to play the game and use GPT-4 to automatically convert the game logs …

abstract adventure adventure game arxiv cs.ai cs.cl emergence evolution explore game language language models large language large language models llm llms narrative solve text type