Augmented Algorithm

DESCRIPTION

Learning data structures and algorithms is a fundamental activity in computer science education, but this is challenging due to their abstract and dynamic nature. While algorithm visualization tools have shown pedagogical benefits, they remain underutilized in educational settings due to creation or integration difficulties. We introduce Augmented Algorithm, a novel LLM-powered algorithm visualization tool that transforms static textbook pseudocode into embedded, interactive algorithm visualizations. Our web-based system combines computer vision with LLMs to automatically generate synchronized, step-by-step algorithm animations from pseudocode directly within scanned textbook pages. We evaluated Augmented Algorithm through technical evaluation, a usability study with students (N=15), and expert interviews with instructors (N=6). Results show that our system significantly reduces algorithm visualization development and access effort while enabling more interactive and tailored learning experiences for algorithmic concepts.

TECHNOLOGY

This system is implemented with range of powerful tools, including React, Next.js, Tailwind CSS, D3.js, FastAPI, Langgraph, AWS Lambda, and Neon.