Design Techniques for LLM-Powered Interactive Storytelling: A Case Study of the Dramamancer System
This addresses the problem of enhancing interactive narrative experiences for authors and players, but it appears incremental as it builds on existing LLM capabilities without claiming major breakthroughs.
The paper tackles the challenge of integrating authorial intent with player agency in interactive storytelling by introducing Dramamancer, a system that uses an LLM to transform story schemas into player-driven narratives, though no concrete results or numbers are provided.
The rise of Large Language Models (LLMs) has enabled a new paradigm for bridging authorial intent and player agency in interactive narrative. We consider this paradigm through the example of Dramamancer, a system that uses an LLM to transform author-created story schemas into player-driven playthroughs. This extended abstract outlines some design techniques and evaluation considerations associated with this system.