NarrativeLoom: Enhancing Creative Storytelling through Multi-Persona Collaborative Improvisation

TL;DR

NarrativeLoom is a multi-persona AI storytelling system that enhances narrative diversity and creativity by combining AI-generated options with user selection, grounded in creativity theory, and validated through a controlled user study.

Contribution

This paper introduces NarrativeLoom, a novel co-creative storytelling system using multiple AI personas and theory-based design, improving narrative originality and user engagement.

Findings

Stories are more diverse and creative with NarrativeLoom.

Users perceive stories as more novel and richer.

Expert ratings confirm improved creativity dimensions.

Abstract

Large Language Models show promise for AI-assisted storytelling, yet current tools often generate predictable, unoriginal narratives. To address this limitation, we present NarrativeLoom, a multi-persona co-creative system grounded in Campbell's Blind Variation and Selective Retention theory. NarrativeLoom deploys specialized AI personas to generate diverse narrative options (blind variation), while users act as creative directors to select and refine them (selective retention). We designed a controlled study with 50 participants and found that stories co-authored with NarrativeLoom were not only perceived by users as more novel and diverse but were also objectively rated by experts as significantly better across all Torrance Test creativity dimensions: fluency, flexibility, originality, and elaboration. Stories are significantly longer with richer settings and more dialogue. Writing expertise emerged as a moderator: novices benefited more from structured scaffolding. This demonstrates the value of theory-informed co-creative systems and the importance of adapting them to varying user expertise.