Integrating AI Tutors in a Programming Course

TL;DR

This paper presents RAGMan, an LLM-powered tutoring system integrated into an introductory programming course, demonstrating high accuracy and positive student feedback in supporting homework and learning.

Contribution

Introduces RAGMan, a novel retrieval-augmented LLM tutoring system tailored for course-specific support, with deployment and evaluation in a real university setting.

Findings

98% accuracy in responding to legitimate homework questions

78% of students reported improved learning experience

Half of the students engaged with the AI tutors

Abstract

RAGMan is an LLM-powered tutoring system that can support a variety of course-specific and homework-specific AI tutors. RAGMan leverages Retrieval Augmented Generation (RAG), as well as strict instructions, to ensure the alignment of the AI tutors' responses. By using RAGMan's AI tutors, students receive assistance with their specific homework assignments without directly obtaining solutions, while also having the ability to ask general programming-related questions. RAGMan was deployed as an optional resource in an introductory programming course with an enrollment of 455 students. It was configured as a set of five homework-specific AI tutors. This paper describes the interactions the students had with the AI tutors, the students' feedback, and a comparative grade analysis. Overall, about half of the students engaged with the AI tutors, and the vast majority of the interactions were legitimate homework questions. When students posed questions within the intended scope, the AI tutors delivered accurate responses 98% of the time. Within the students used AI tutors, 78% reported that the tutors helped their learning. Beyond AI tutors' ability to provide valuable suggestions, students reported appreciating them for fostering a safe learning environment free from judgment.