Towards Dialogic Education through Child-Robot Interaction: A Hybrid Child-Centered Framework

This paper presents ongoing doctoral research on Dialogic Educational Child-Robot Interaction (DECRI), focused on designing child-centered hybrid dialogue systems that combine dialogic pedagogical structure with the adaptive potential of LLMs. We propose a generalisable framework that facilitates personalized educational dialogues, and validate its feasibility in a study (N=101) aimed at enhancing reading motivation. The framework integrates pedagogically grounded, co-designed dialogue strategies with LLM capabilities to support meaningful personalization. Future directions include expanding to small-group settings, leveraging local LLMs for enhanced personalization, co-design, and early user model development, and developing AI-based validation tools. The overarching goal is to responsibly design DECRI tailored to each child, while maintaining pedagogical and developmental integrity.