Research

Paper

AI LLM February 25, 2026

StoryComposerAI: Supporting Human-AI Story Co-Creation Through Decomposition and Linking

Authors

Shuo Niu, Dylan Clements, Marina Margalit Nemanov, Hyungsin Kim

Abstract

GenAI's ability to produce text and images is increasingly incorporated into human-AI co-creation tasks such as storytelling and video editing. However, integrating GenAI into these tasks requires enabling users to retain control over editing individual story elements while ensuring that generated visuals remain coherent with the storyline and consistent across multiple AI-generated outputs. This work examines a paradigm of creative decomposition and linking, which allows creators to clearly communicate creative intent by prompting GenAI to tailor specific story elements, such as storylines, personas, locations, and scenes, while maintaining coherence among them. We implement and evaluate StoryComposerAI, a system that exemplifies this paradigm for enhancing users' sense of control and content consistency in human-AI co-creation of digital stories.

Metadata

arXiv ID: 2602.21486
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-02-25
Fetched: 2026-02-26 05:00

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.21486v1</id>\n    <title>StoryComposerAI: Supporting Human-AI Story Co-Creation Through Decomposition and Linking</title>\n    <updated>2026-02-25T01:33:49Z</updated>\n    <link href='https://arxiv.org/abs/2602.21486v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.21486v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>GenAI's ability to produce text and images is increasingly incorporated into human-AI co-creation tasks such as storytelling and video editing. However, integrating GenAI into these tasks requires enabling users to retain control over editing individual story elements while ensuring that generated visuals remain coherent with the storyline and consistent across multiple AI-generated outputs. This work examines a paradigm of creative decomposition and linking, which allows creators to clearly communicate creative intent by prompting GenAI to tailor specific story elements, such as storylines, personas, locations, and scenes, while maintaining coherence among them. We implement and evaluate StoryComposerAI, a system that exemplifies this paradigm for enhancing users' sense of control and content consistency in human-AI co-creation of digital stories.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <published>2026-02-25T01:33:49Z</published>\n    <arxiv:comment>Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems (CHI EA '26)</arxiv:comment>\n    <arxiv:primary_category term='cs.HC'/>\n    <author>\n      <name>Shuo Niu</name>\n    </author>\n    <author>\n      <name>Dylan Clements</name>\n    </author>\n    <author>\n      <name>Marina Margalit Nemanov</name>\n    </author>\n    <author>\n      <name>Hyungsin Kim</name>\n    </author>\n    <arxiv:doi>10.1145/3772363.3798629</arxiv:doi>\n    <link href='https://doi.org/10.1145/3772363.3798629' rel='related' title='doi'/>\n  </entry>"
}