Joshua Glazer | Searcharxiv

arXiv2026

From Prompt to Embodied Simulation: Using Generative AI to Create AR Physics Learning Tools

Spread your thumb and index finger in the air, and a virtual lamp in the room changes color. Computer simulations have a long and well-documented record of supporting physics learning. They can support the understanding of abstract physical concepts by making them interactive and by inviting students to play with parameters and explore them. In this paper, we show how a structured natural-language prompt can generate a browser-based, hand-controlled augmented-reality (AR) physics simulation, and we describe its use in an introductory physics class.

physics.ed-ph↗

arXiv2024

Leveraging AI for Rapid Generation of Physics Simulations in Education: Building Your Own Virtual Lab

Seemingly we are not so far from Star Trek's food replicator. Generative artificial intelligence is rapidly becoming an integral part of both science and education, offering not only automation of processes but also the dynamic creation of complex, personalized content for educational purposes. With such advancement, educators are now crafting exams, building tutors, creating writing partners for students, and developing an array of other powerful tools for supporting our educational practices and student learning. We share a new class of opportunities for supporting learners and educators through the development of AI-generated simulations of physical phenomena and models. While we are not at the stage of "Computer: make me a mathematical simulation depicting the quantum wave functions of electrons in the hydrogen atom", we are not far off.

physics.ed-ph↗