Our Coding Adventure

Using LLMs to Personalise the Narrative of a Tangible Programming Robot for Preschoolers.

This is the code accompanying a publication at D-SAIL Workshop - Transformative Curriculum Design: Digitalisation, Sustainability, and AI Literacy for 21st Century Learning, held on July 22nd, 2025 in conjunction with 26th International Conference on Artificial Intelligence in Education in Palermo, Italy.

Abstract: Finding balanced ways to employ Large Language Models (LLMs) in education is a challenge due to inherent risks of poor understanding of the technology and of a susceptible audience. This is particularly so with younger children, who are known to have difficulties with pervasive screen time. Working with a tangible programming robot called Cubetto, we propose an approach to benefit from the capabilities of LLMs by employing such models in the preparation of personalised storytelling, necessary for preschool children to get accustomed to the practice of commanding the robot. We engage in action research to develop an early version of a formalised process to rapidly prototype game stories for Cubetto. Our approach has both reproducible results, because it employs open weight models, and is model-agnostic, because we test it with 5 different LLMs. We document on one hand the process, the used materials and prompts, and on the other the learning experience and outcomes. We deem the generation successful for the intended purposes of using the results as a teacher aid. Testing the models on 4 different task scenarios, we encounter issues of consistency and hallucinations and document the corresponding evaluation process and attempts (some successful and some not) to overcome these issues. Importantly, the process does not expose children to LLMs directly. Rather, the technology is used to help teachers easily develop personalised narratives on children's preferred topics. We believe our method is adequate for preschool classes and we are planning to further experiment in real-world educational settings.

Keywords: tangible programming, preschool education, LLM storytelling, open weights models

The script to reproduct this research is our_coding_adventure.ipynb.

Cite as (BibTex):

Ruskov, M. (2025). Our Coding Adventure: Using LLMs to Personalise the Narrative of a Tangible Programming Robot for Preschoolers. In: *Proceedings of the D-SAIL Workshop - Transformative Curriculum Design: Digitalisation, Sustainability, and AI Literacy for 21st Century Learning*. Palermo, Italy.