Player-Driven Emergence in LLM-Driven Game Narrative

TL;DR

This paper investigates how large language models can enable emergent, player-driven narratives in text-based games, revealing new story nodes and enhancing engagement through interactive AI-generated characters.

Contribution

It introduces a novel framework for analyzing emergent narrative behaviors in LLM-driven games and demonstrates how player interactions lead to unexpected story developments.

Findings

Players discover new, engaging narrative nodes through interaction with LLMs.

Players who enjoy exploration tend to create more emergent story elements.

LLMs facilitate emergent storytelling beyond predefined narratives.

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 into a node-graph representing the narrative in the player's gameplay. We find that through their interactions with the non-deterministic behavior of the LLM, players are able to discover interesting new emergent nodes that were not a part of the original narrative but have potential for being fun and engaging. Players that created the most emergent nodes tended to be those that often enjoy games that facilitate discovery, exploration and experimentation.