This paper discusses a study on emergent behaviors in game narratives through player interaction with large language models (LLMs). The game is a text-adventure where players solve a mystery, interacting with characters generated by GPT-4. The study involved 28 gamers whose gameplay was converted into a node-graph narrative. It was observed that players' interactions with the LLM led to the discovery of new, engaging narrative elements not originally planned. Players who enjoyed exploration and experimentation in games tended to discover more of these emergent narrative nodes.
This paper presents a novel tool called GRIM, which stands for Graph-based Interactive narrative visualization for gaMes. GRIM uses GPT-4 to generate branching narratives for dialogue-based RPG games, given a high-level description and some constraints. GRIM also allows the game designer to edit the narrative graph and automatically creates new sub-graphs to fit the edits. The authors evaluate GRIM by using it to create stories for five fairy tales and get feedback from three game designers.
This paper shows how to use OpenAI Codex, a model that can generate code and natural language, to create NPCs that can talk and act in Minecraft. The authors use a few examples of how to ask Codex to make code, chat, and answer questions. They test their approach with real gamers and find some limitations and possible solutions.