# Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling

arXiv: https://arxiv.org/abs/2402.01927 · HTML: https://mlsanity.com/paper/2402.01927/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Feb 2024.

## Built on by (most cited first, 21 of 21)

- [MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education](https://mlsanity.com/paper/2404.06711/) (2024)
- [MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions](https://mlsanity.com/paper/2405.19444/) (2024)
- [PeerGPT: Probing the Roles of LLM-based Peer Agents as Team Moderators and Participants in Children's Collaborative Learning](https://mlsanity.com/paper/2403.14227/) (2024)
- [Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review](https://mlsanity.com/paper/2501.12557/) (2025)
- [Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation](https://mlsanity.com/paper/2502.02780/) (2025)
- [Biased Tales: Cultural and Topic Bias in Generating Children's Stories](https://mlsanity.com/paper/2509.07908/) (2025)
- [GPT for Games: An Updated Scoping Review (2020-2024)](https://mlsanity.com/paper/2411.00308/) (2024)
- [Benchmarking LLMs for Mimicking Child-Caregiver Language in Interaction](https://mlsanity.com/paper/2412.09318/) (2024)
- [Bridging the AI Adoption Gap: Designing an Interactive Pedagogical Agent for Higher Education Instructors](https://mlsanity.com/paper/2503.05039/) (2025)
- [An LLM-enabled Multi-Agent Autonomous Mechatronics Design Framework](https://mlsanity.com/paper/2504.14681/) (2025)
- [ELI-Why: Evaluating the Pedagogical Utility of Language Model Explanations](https://mlsanity.com/paper/2506.14200/) (2025)
- [Narrix: Remixing Narrative Strategies from Examples for Story Writing](https://mlsanity.com/paper/2604.07643/) (2026)
- [Social Life Simulation for Non-Cognitive Skills Learning](https://mlsanity.com/paper/2405.00273/) (2024)
- [DinoCompanion: An Attachment-Theory Informed Multimodal Robot for Emotionally Responsive Child-AI Interaction](https://mlsanity.com/paper/2506.12486/) (2025)
- [Elementary School Students' and Teachers' Perceptions Towards Creative Mathematical Writing with Generative AI](https://mlsanity.com/paper/2409.06723/) (2024)
- [Once Upon an AI: Six Scaffolds for Child-AI Interaction Design, Inspired by Disney](https://mlsanity.com/paper/2504.08670/) (2025)
- [Empowering Children to Create AI-Enabled Augmented Reality Experiences](https://mlsanity.com/paper/2508.08467/) (2025)
- [RoboBuddy in the Classroom: Exploring LLM-Powered Social Robots for Storytelling in Learning and Integration Activities](https://mlsanity.com/paper/2508.16706/) (2025)
- [A Privacy by Design Framework for Large Language Model-Based Applications for Children](https://mlsanity.com/paper/2602.17418/) (2026)
- [ELLA: Generative AI-Powered Social Robots for Early Language Development at Home](https://mlsanity.com/paper/2603.12508/) (2026)
- [BotDirector: Robot Storytelling Across the Symmetrical Reality with Multi-modal Interactions](https://mlsanity.com/paper/2606.03223/) (2026)

## Abstract (arXiv)

Mathematical language is a cornerstone of a child's mathematical development, and children can effectively acquire this language through storytelling with a knowledgeable and engaging partner. In this study, we leverage the recent advances in large language models to conduct free-form, creative conversations with children. Consequently, we developed Mathemyths, a joint storytelling agent that takes turns co-creating stories with children while integrating mathematical terms into the evolving narrative. This paper details our development process, illustrating how prompt-engineering can optimize LLMs for educational contexts. Through a user study involving 35 children aged 4-8 years, our results suggest that when children interacted with Mathemyths, their learning of mathematical language was comparable to those who co-created stories with a human partner. However, we observed differences in how children engaged with co-creation partners of different natures. Overall, we believe that LLM applications, like Mathemyths, offer children a unique conversational experience pertaining to focused learning objectives.