Pensieve Discuss: Scalable Small-Group CS Tutoring System with AI
Yoonseok Yang, Jack Liu, J. D. Zamfirescu-Pereira, John DeNero
TL;DR
Pensieve Discuss tackles the scalability challenge of small-group CS tutoring by integrating synchronized collaborative editing with AI and teaching assistants in real-time. The system was deployed in a CS1 course with 800 students, enabling groups to solve scaffolded problems while receiving AI and TA guidance. Results show increased student collaboration, high AI-tutor usefulness, greater satisfaction, and a substantial rise in student questions, indicating the value of human-in-the-loop AI in group tutoring. The work demonstrates the feasibility and benefits of applying LLM-based assistance within small-group settings and points to future research directions in educational AI for scalable, collaborative learning.
Abstract
Small-group tutoring in Computer Science (CS) is effective, but presents the challenge of providing a dedicated tutor for each group and encouraging collaboration among group members at scale. We present Pensieve Discuss, a software platform that integrates synchronous editing for scaffolded programming problems with online human and AI tutors, designed to improve student collaboration and experience during group tutoring sessions. Our semester-long deployment to 800 students in a CS1 course demonstrated consistently high collaboration rates, positive feedback about the AI tutor's helpfulness and correctness, increased satisfaction with the group tutoring experience, and a substantial increase in question volume. The use of our system was preferred over an interface lacking AI tutors and synchronous editing capabilities. Our experiences suggest that small-group tutoring sessions are an important avenue for future research in educational AI.