Foto von Marvin Meyer auf Unsplash

IRIS – Towards AI-driven interactive learning

IRIS is an advanced AI-driven virtual tutor designed to provide personalized and context-aware support to computer science students as they tackle programming tasks. Instead of offering complete solutions, IRIS encourages independent thinking and problem-solving through subtle hints and counter-questions. Additionally, IRIS can access lecture content, enabling it to tap into course-specific knowledge for more tailored and relevant responses. IRIS is integrated into Artemis, a learning and research platform focusing on individual feedback to support interactive and adaptive learning. 

Target Group

Computer Science Students

Vision

The integration of artificial intelligence in the education sector is experiencing significant growth. Researchers of the applied software engineering department at TUM actively engage in this transformation by facilitating an optimized and personalized learning experience with IRIS. IRIS is not a replacement for human tutors but a valuable tool that assists students in enhancing their problem-solving abilities and reaching their full potential. Students are encouraged to apply critical thinking and judgment when using IRIS-generated content.

Mission

Iris is a context-aware assistant in large-scale educational settings based on Generative AI technology. 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. This approach is intended to encourage students to think for themselves. To boost learning efficiency, the chatbot only answers questions directly relevant to the learning content.  

The long-term goal is to evolve IRIS into a comprehensive “Study Buddy” that accompanies students through all aspects of their learning journey, supporting them in everything from daily study activities to exam preparation. 

Project Outline

In the upcoming development phases, IRIS will be enhanced with proactive features, allowing it to automatically reach out to students when it detects potential issues or struggles. Moreover, IRIS will expand to include support for acquiring and maintaining long-term memory, support of additional exercise types, automated communication, and knowledge extraction from lecture recordings, making the learning experience even more interactive and effective.
Principal Investigators

Prof. Dr. Stephan Krusche, Patrick Bassner

Contact

Patrick Bassner, patrick.bassner@tum.de

Website

https://ase.cit.tum.de/

  • Study: Patrick Bassner, Eduard Frankford, and Stephan Krusche. 2024. Iris: An AI-Driven Virtual Tutor for Computer Science Education. In: Proceedings of the 2024 on Innovation and Technology in Computer Science Education V. 1 (ITiCSE 2024). Association for Computing Machinery, New York, NY, USA, 394–400. 
Tags
Share it

Related Topics