Toward Personalizing Quantum Computing Education: An Evolutionary LLM-Powered Approach

2025-04-24

AI Summary

Quantum computing education faces challenges including conceptual abstraction, poor tool adaptability, and insufficient personalization. To address these, this paper proposes a knowledge graph–driven dual-LLM agent framework: a pedagogical agent dynamically models student cognitive states and generates adaptive learning paths in real time, while a lesson-planning agent autonomously refines instructional materials based on interaction trajectories. We introduce a novel user-intervenable tagging mechanism to mitigate LLM hallucination and enable self-evolving pedagogical reasoning. The system integrates domain-specific knowledge graphs, multi-agent coordination, interactive feedback loops, and context-aware generation. Experimental results demonstrate that our approach accurately captures fine-grained learning behaviors, significantly improving instructional adaptivity, controllability, and tutoring efficacy. It establishes a scalable, interpretable paradigm for AI-augmented quantum education.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Knowledge Representation and Reasoning: Qualitative Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Quantum computing education faces significant challenges due to its complexity and the limitations of current tools; this paper introduces a novel Intelligent Teaching Assistant for quantum computing education and details its evolutionary design process. The system combines a knowledge-graph-augmented architecture with two specialized Large Language Model (LLM) agents: a Teaching Agent for dynamic interaction, and a Lesson Planning Agent for lesson plan generation. The system is designed to adapt to individual student needs, with interactions meticulously tracked and stored in a knowledge graph. This graph represents student actions, learning resources, and relationships, aiming to enable reasoning about effective learning pathways. We describe the implementation of the system, highlighting the challenges encountered and the solutions implemented, including introducing a dual-agent architecture where tasks are separated, all coordinated through a central knowledge graph that maintains system awareness, and a user-facing tag system intended to mitigate LLM hallucination and improve user control. Preliminary results illustrate the system's potential to capture rich interaction data, dynamically adapt lesson plans based on student feedback via a tag system in simulation, and facilitate context-aware tutoring through the integrated knowledge graph, though systematic evaluation is required.

Problem

• Personalizing quantum computing education for individual needs
• Overcoming complexity and tool limitations in quantum education
• Mitigating LLM hallucination and enhancing user control

Innovation

• Knowledge-graph-augmented LLM architecture
• Dual-agent system for teaching and planning
• Tag system to reduce LLM hallucination