Iris: An AI-Driven Virtual Tutor For Computer Science Education
Patrick Bassner, Eduard Frankford, Stephan Krusche
TL;DR
The paper addresses scalability in computer science education by introducing Iris, an AI-driven virtual tutor integrated into the Artemis learning platform to deliver personalized, context-aware programming guidance while withholding complete solutions. Iris relies on a Chain-of-Thought prompting framework and a role-based tutor persona to provide calibrated hints and counter-questions, using problem statements, student code, and automated feedback to tailor responses. An online survey with three CS1 courses assesses students' subjective experiences, revealing strong perceived understanding and engagement, high safety in asking questions, and a tendency to view Iris as a complement rather than a replacement for human tutors, with limited reliance in exam contexts. The findings point to Iris’s potential to enhance practice-based learning while underscoring the need for improved context access, careful management of dependence, and future exploration of more advanced LLMs and embedding-based code retrieval to further bolster educational impact.
Abstract
Integrating AI-driven tools in higher education is an emerging area with transformative potential. This paper introduces Iris, a chat-based virtual tutor integrated into the interactive learning platform Artemis that offers personalized, context-aware assistance in large-scale educational settings. Iris supports computer science students by guiding them through programming exercises and is designed to act as a tutor in a didactically meaningful way. Its calibrated assistance avoids revealing complete solutions, offering subtle hints or counter-questions to foster independent problem-solving skills. For each question, it issues multiple prompts in a Chain-of-Thought to GPT-3.5-Turbo. The prompts include a tutor role description and examples of meaningful answers through few-shot learning. Iris employs contextual awareness by accessing the problem statement, student code, and automated feedback to provide tailored advice. An empirical evaluation shows that students perceive Iris as effective because it understands their questions, provides relevant support, and contributes to the learning process. While students consider Iris a valuable tool for programming exercises and homework, they also feel confident solving programming tasks in computer-based exams without Iris. The findings underscore students' appreciation for Iris' immediate and personalized support, though students predominantly view it as a complement to, rather than a replacement for, human tutors. Nevertheless, Iris creates a space for students to ask questions without being judged by others.