Our Coding Adventure: Using LLMs to Personalise the Narrative of a Tangible Programming Robot for Preschoolers

2025-06-25

AI Summary

This study addresses safety and age-appropriateness challenges in applying large language models (LLMs) to preschool education—specifically, generating personalized narrative content for screen-free programming learning while strictly limiting children’s screen time. We propose a model-agnostic, reproducible rapid prototyping workflow: leveraging five open-source LLMs to automatically generate pedagogically aligned stories for the tangible programming robot Cubetto, with teachers fully controlling prompt engineering and content curation, and children having zero direct interaction with the models. An action research cycle iteratively refined prompting strategies and generation pipelines to enhance efficiency and fidelity. Results demonstrate significantly improved teacher productivity in educational content creation and high classroom suitability of generated narratives. The key contribution is a novel “LLM-augmented but child-isolated” paradigm for early childhood education—ensuring AI support remains safe, teacher-mediated, and scalable, thereby offering a responsible, controllable, and generalizable technical pathway for AI integration in early learning.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Balancing LLM use in preschool education to mitigate risks
• Personalizing storytelling for tangible robot programming with LLMs
• Addressing LLM consistency issues in educational content generation

Innovation

• Using LLMs to personalize tangible robot narratives
• Action research for formalized story prototyping
• Model-agnostic approach with open weight LLMs