Towards Enhanced Immersion and Agency for LLM-based Interactive Drama
This work addresses the underexplored aspects of immersion and agency for players in interactive drama, representing an incremental improvement in this domain-specific scenario.
The paper tackled the problem of enhancing immersion and agency in LLM-based interactive drama by proposing Playwriting-guided Generation and Plot-based Reflection, resulting in improved story structures and narrative quality as evaluated through human judgment.
LLM-based Interactive Drama is a novel AI-based dialogue scenario, where the user (i.e. the player) plays the role of a character in the story, has conversations with characters played by LLM agents, and experiences an unfolding story. This paper begins with understanding interactive drama from two aspects: Immersion, the player's feeling of being present in the story, and Agency, the player's ability to influence the story world. Both are crucial to creating an enjoyable interactive experience, while they have been underexplored in previous work. To enhance these two aspects, we first propose Playwriting-guided Generation, a novel method that helps LLMs craft dramatic stories with substantially improved structures and narrative quality. Additionally, we introduce Plot-based Reflection for LLM agents to refine their reactions to align with the player's intentions. Our evaluation relies on human judgment to assess the gains of our methods in terms of immersion and agency.