aiqbench analysis
This research investigates how conversation design and prompt framing influence the quality of collaborative storytelling between children (ages 6-8) and conversational AI agents. By integrating tangible interfaces like NFC toys with voice dialogue, the study demonstrates that specific educational scaffolding significantly shapes a child's narrative contributions and engagement consistency. The work advances our understanding of human-AI interaction in co-creative settings, moving beyond standard chatbots to systems designed for developmental learning.
Tinker Tales: A Tangible Dialogue System for Child-AI Co-Creative Storytelling
arXiv:2602.04109v3 Announce Type: replace-cross Abstract: Conversational AI agents are increasingly explored as creative partners, yet how conversation design shapes child-AI dialogue in co-creative settings remains underexplored. We present Tinker Tales, a tangible dialogue system for child-AI collaborative storytelling, in which educational frameworks (narrative development and social-emotional learning) are instantiated as conversation design, shaping how the agent engages children across four narrative stages. The system combines a physical storytelling board, NFC-embedded toys, and a mobile app mediating multimodal interaction through tangible manipulation and voice-based dialogue. We conducted a home-based user study with 10 children (ages 6-8) across two conversation design conditions varying in how the agent structured elaboration, with and without educational scaffolding. Our findings show that prompt framing shapes the form and consistency of children's narrative contributions, structuring how they participate in co-creative dialogue with AI.
Abstract:Conversational AI agents are increasingly explored as creative partners, yet how conversation design shapes child-AI dialogue in co-creative settings remains underexplored. We present Tinker Tales, a tangible dialogue system for child-AI collaborative storytelling, in which educational frameworks (narrative development and social-emotional learning) are instantiated as conversation design, shaping how the agent engages children across four narrative stages. The system combines a physical storytelling board, NFC-embedded toys, and a mobile app mediating multimodal interaction through tangible manipulation and voice-based dialogue. We conducted a home-based user study with 10 children (ages 6-8) across two conversation design conditions varying in how the agent structured elaboration, with and without educational scaffolding. Our findings show that prompt framing shapes the form and consistency of children's narrative contributions, structuring how they participate in co-creative dialogue with AI.
Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
arXiv:2602.04109 [cs.HC]
(or arXiv:2602.04109v3 [cs.HC] for this version)
https://doi.org/10.48550/arXiv.2602.04109 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 226 words
Related coverage
Biological Superintelligence
LessWrong · Jul 30, 2026

AI bots started a religion — humans immediately followed
The Verge · Aug 6, 2026
BotDirector: Robot Storytelling Across the Symmetrical Reality with Multi-modal Interactions
arXiv · Jun 3, 2026

When will average people feel AI’s impact?
Interconnects · Sep 9, 2026