MicroSims: A Framework for AI-Generated, Scalable Educational Simulations with Universal Embedding and Adaptive Learning Support

TL;DR

MicroSims tackles the problem of costly, complex, and platform-locked educational simulations by introducing an AI-assisted framework for lightweight, browser-based simulations that can be universally embedded via iframes. The approach combines standardized design patterns, a width-responsive, sandboxed technical architecture, and a Dublin Core–driven metadata/discovery system to enable rapid generation, customization, and deployment across diverse learning environments. Key contributions include a comprehensive design framework, AI-compatible standardization, universal embedding, a structured development workflow, and empirical grounding from PhET-style learning research, all aimed at supporting scalable, equitable access to interactive learning tools. The work demonstrates potential for low-cost intelligent textbooks and adaptive learning systems, with significant implications for educational equity and the future of AI-powered, on-demand curriculum-aligned simulations.

Abstract

Educational simulations have long been recognized as powerful tools for enhancing learning outcomes, yet their creation has traditionally required substantial resources and technical expertise. This paper introduces MicroSims a novel framework for creating lightweight, interactive educational simulations that can be rapidly generated using artificial intelligence, universally embedded across digital learning platforms, and easily customized without programming knowledge. MicroSims occupy a unique position at the intersection of three key innovations: (1) standardized design patterns that enable AI-assisted generation, (2) iframe-based architecture that provides universal embedding and sandboxed security, and (3) transparent, modifiable code that supports customization and pedagogical transparency. We present a comprehensive framework encompassing design principles, technical architecture, metadata standards, and development workflows. Drawing on empirical research from physics education studies and meta-analyses across STEM disciplines, we demonstrate that interactive simulations can improve conceptual understanding by up to 30-40\% compared to traditional instruction. MicroSims extend these benefits while addressing persistent barriers of cost, technical complexity, and platform dependence. This work has significant implications for educational equity, and low-cost intelligent interactive textbooks that enabling educators worldwide to create customized, curriculum-aligned simulations on demand. We discuss implementation considerations, present evidence of effectiveness, and outline future directions for AI-powered adaptive learning systems built on the MicroSim foundation.

Figures (4)

• Figure 1: MicroSims occupy a unique position at the intersection of three critical characteristics: Simplicity (lightweight, focused scope), Accessibility (browser-based, universal embedding), and AI Generation (standardized patterns, prompt-compatible). This convergence of attributes distinguishes MicroSims from other educational technology approaches and enables their scalable deployment across diverse learning contexts.
• Figure 2: MicroSims use a standardized layout pattern with distinct areas for visualization and user controls. This consistent structure facilitates generative AI creation and modification of MicroSims while ensuring usability across diverse educational contexts. This layout consistency also allows interactivity to be logged in a standardized way for integration with intelligent textbooks and learning analytics systems.
• Figure 3: MicroSims use a standardized web deployment architecture depicted as a series of layers. The foundation is built on HTML-5, JavaScript standards (ECMAScript), ensuring broad compatibility across browsers and devices. Modern browsers such as Chrome ane FireFox can leverage consistent low-level drawing libraries such as WebGL and WebGPU for fast rendering of complex 3D simulations. The p5.js library provides the core drawing and interaction capabilities, while the MicroSims framework extends p5.js with standardized patterns for responsive design, user interface management, and educational data collection. This layered architecture supports seamless embedding within iframe elements, enabling integration with diverse educational platforms while maintaining security and performance. A MicroSIm can optionally generate xAPI JSON statements to report user interactions to learning record stores for integration with intelligent textbooks and learning analytics systems. Analysis of student interaction data can be used to adaptively modify the simulation experience using reinforcement learning techniques.
• Figure 4: Learning effectiveness of interactive simulations compared to traditional instruction across three key outcome measures. Data represent meta-analysis findings from multiple studies including PhET Interactive Simulations research and systematic reviews across STEM disciplines. Error bars indicate reported ranges of improvement. Sources: Wieman et al. (2008), Adams et al. (2008), D'Angelo et al. (2014), Rutten et al. (2012), Smetana & Bell (2012).