Static Vs. Agentic Game Master AI for Facilitating Solo Role-Playing Experiences
This work addresses the challenge of enhancing interactive fiction for solo role-playing gamers, though it appears incremental as it builds on existing AI methods for narrative generation.
The paper tackled the problem of creating a game master AI for solo role-playing games by developing two versions: v1 with simplified prompt engineering and v2 using a multi-agent architecture with ReAct for reasoning and action. The result showed that v2 significantly improved modularity, game experience, immersion, and curiosity compared to v1.
This paper presents a game master AI for single-player role-playing games. The AI is designed to deliver interactive text-based narratives and experiences typically associated with multiplayer tabletop games like Dungeons & Dragons. We report on the design process and the series of experiments to improve the functionality and experience design, resulting in two functional versions of the system. While v1 of our system uses simplified prompt engineering, v2 leverages a multi-agent architecture and the ReAct framework to include reasoning and action. A comparative evaluation demonstrates that v2 as an agentic system maintains play while significantly improving modularity and game experience, including immersion and curiosity. Our findings contribute to the evolution of AI-driven interactive fiction, highlighting new avenues for enhancing solo role-playing experiences.