From Prototype to Classroom: An Intelligent Tutoring System for Quantum Education

Researchers from Old Dominion University (Elhaimeur & Chrisochoides) present ITAS (Intelligent Teaching Assistant System), a multi-agent tutoring system designed to tackle the unique challenges of quantum computing education. Building on a prior prototype that was validated only on simulated runs, ITAS introduces four key contributions: a five-module QIS curriculum based on Watrous's information-first framework, a Spoke-and-Wheel teaching architecture with quantum-specialized LLM agents (a Teaching Agent for dynamic interaction and a Lesson Planning Agent for lesson generation), a production-grade cloud infrastructure built for regulatory compliance, and a conversational analytics layer for instructors. The system was piloted in a real quantum computing course at Old Dominion University, and results indicate that agent specialization resolves the task-boundary failures seen in the prototype, cloud infrastructure supports classroom-scale concurrency at sub-textbook cost, and the analytics agent surfaces curriculum gaps invisible to the instructor.

The paper addresses three critical questions that the prototype could not answer: whether agent specialization solves reliability in quantum information science, whether the system can run in a real course (not just a demo), and whether instructors gain actionable intelligence. Early deployment evidence is consistent with specialization fixing task-boundary failures, and the analytics agent provides instructors with insights like curriculum gaps they could not otherwise see. The system is designed for production use and regulatory compliance, making it a viable tool for scaling quantum education beyond well-resourced institutions. The paper is submitted to IEEE QCE 2026, with companion papers on architecture and latency analysis in preparation.