π€ AI Summary
This study addresses the challenge of efficiently transforming personalized narratives into immersive live-action role-playing (LARP) experiences. We propose a VR-native narrative framework integrating generative AI and intelligent agents: large language models (LLMs) enable collaborative, real-time co-creation of dynamic story worlds and characters with users, while lightweight, editable agent architectures support responsive behavior evolution and contextual adaptation; all narrative content is rendered and interacted with end-to-end within the VR environment. Our key contribution is the first holistic integration of generative AI, editable agent systems, and VR-based LARPβenabling users to simultaneously assume both authorial and participatory roles. Evaluation results demonstrate significant improvements in narrative personalization, character consistency, and immersion, outperforming baseline systems in user engagement and interaction naturalness.
π Abstract
We introduce GenLARP, a virtual reality (VR) system that transforms personalized stories into immersive live action role-playing (LARP) experiences. GenLARP enables users to act as both creators and players, allowing them to design characters based on their descriptions and live in the story world. Generative AI and agents powered by Large Language Models (LLMs) enrich these experiences.