Towards Enhanced Immersion and Agency for LLM-based Interactive Drama

TL;DR

This paper proposes novel methods to improve immersion and agency in LLM-based interactive drama by guiding story generation and refining agent reactions, validated through human judgment assessments.

Contribution

It introduces Playwriting-guided Generation and Plot-based Reflection to enhance narrative quality and player influence in interactive drama.

Findings

Improved narrative structure and quality in generated stories.

Enhanced player immersion and sense of agency.

Positive human judgment feedback on proposed methods.

Abstract

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.