AITEE -- Agentic Tutor for Electrical Engineering

TL;DR

AITEE tackles the challenge of scalable, reliable electrical engineering tutoring by integrating circuit reconstruction, graph-based context retrieval, retrieval-augmented generation, and SPICE simulation within a Socratic-dialogue framework. The system converts hand-drawn and digital circuits into netlists, embeds them with a graph neural network, and retrieves lecture-context through cosine-based embeddings, augmented by MRI indexing and simulation-based validation. Empirical results show that MRI with 1-Shot-CoT and Sim yields tutor-level performance for most models, while didactic prompts substantially improve learner autonomy and dialogue robustness; arithmetic accuracy and robustness for complex superposition tasks remain challenging. This work demonstrates a scalable path toward personalized EE education, enabling reliable, interactive tutoring that can operate with both sketches and schematics, and highlights practical directions for student-in-the-wild evaluation.

Abstract

Intelligent tutoring systems combined with large language models offer a promising approach to address students' diverse needs and promote self-efficacious learning. While large language models possess good foundational knowledge of electrical engineering basics, they remain insufficiently capable of addressing specific questions about electrical circuits. In this paper, we present AITEE, an agent-based tutoring system for electrical engineering designed to accompany students throughout their learning process, offer individualized support, and promote self-directed learning. AITEE supports both hand-drawn and digital circuits through an adapted circuit reconstruction process, enabling natural interaction with students. Our novel graph-based similarity measure identifies relevant context from lecture materials through a retrieval augmented generation approach, while parallel Spice simulation further enhances accuracy in applying solution methodologies. The system implements a Socratic dialogue to foster learner autonomy through guided questioning. Experimental evaluations demonstrate that AITEE significantly outperforms baseline approaches in domain-specific knowledge application, with even medium-sized LLM models showing acceptable performance. Our results highlight the potential of agentic tutors to deliver scalable, personalized, and effective learning environments for electrical engineering education.

Figures (12)

• Figure 1: Exemplary electrical circuit with current and voltage source as well as an ohmic resistor.
• Figure 2:
• Figure 3: Image of a circuit with netlist nodes.
• Figure 4: Netlist of the circuit shown to the left.
• Figure 5: