NarrativeLoom: Enhancing Creative Storytelling through Multi-Persona Collaborative Improvisation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917321455435776 |
|---|---|
| author | Ma, Yuxi Peng, Yongqian Yang, Fengyuan Zha, Siyu Zhang, Chi Jia, Zixia Zheng, Zilong Zhu, Yixin |
| author_facet | Ma, Yuxi Peng, Yongqian Yang, Fengyuan Zha, Siyu Zhang, Chi Jia, Zixia Zheng, Zilong Zhu, Yixin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07155 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NarrativeLoom: Enhancing Creative Storytelling through Multi-Persona Collaborative Improvisation Ma, Yuxi Peng, Yongqian Yang, Fengyuan Zha, Siyu Zhang, Chi Jia, Zixia Zheng, Zilong Zhu, Yixin Human-Computer Interaction Multiagent Systems 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. |
| title | NarrativeLoom: Enhancing Creative Storytelling through Multi-Persona Collaborative Improvisation |
| topic | Human-Computer Interaction Multiagent Systems |
| url | https://arxiv.org/abs/2603.07155 |