Drama Llama: An LLM-Powered Storylets Framework for Authorable Responsiveness in Interactive Narrative

2025-01-15

AI Summary

This study addresses the longstanding challenge in interactive narrative design: balancing authorial control with automated content generation. To resolve this, we propose Storylets—a novel framework leveraging large language models (LLMs) that integrates structured Storylets-based narrative modeling with a natural-language-triggered rule engine. Unlike conventional programming-based pre-specification, authors define conditional logic directly in natural language, enabling controllable, responsive, and open-ended narrative generation. Our framework introduces the first natural-language trigger mechanism, preserving author agency while harnessing LLMs’ emergent storytelling capabilities; it is supported by a human-AI co-authoring toolchain. In an empirical study with six professional narrative designers, the system generated coherent, semantically plausible, and behaviorally credible character interactions. Results validate the feasibility and effectiveness of a hybrid paradigm combining controlled generation with human guidance.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

In this paper, we present Drama Llama, an LLM-powered storylets framework that supports the authoring of responsive, open-ended interactive stories. DL combines the structural benefits of storylet-based systems with the generative capabilities of large language models, enabling authors to create responsive interactive narratives while maintaining narrative control. Rather than crafting complex logical preconditions in a general-purpose or domain-specific programming language, authors define triggers in natural language that fire at appropriate moments in the story. Through a preliminary authoring study with six content authors, we present initial evidence that DL can generate coherent and meaningful narratives with believable character interactions. This work suggests directions for hybrid approaches that enhance authorial control while supporting emergent narrative generation through LLMs.

Problem

• Interactive Storytelling
• Author-Reader Engagement
• Automated Content Generation

Innovation

• Interactive Storytelling
• AI-Assisted Creativity
• Adaptive Narrative