Entry
Debugging with an AI Tutor: Investigating Novice Help-seeking Behaviors and Perceived Learning
Stephanie Yang, Hanzhang Zhao, Yudian Xu, Karen Brennan, Bertrand Schneider
Mixed-methods study (20 students, three time points) of how a pedagogically designed LLM chatbot supports novice debugging in introductory programming; students did not treat the chatbot as primary debugging support and exhibited unproductive use patterns.
·debugging ·help-seeking ·AI tutor ·programming education ·mixed methods
- Impact of ChatGPT on Learning Outcomes and Performance of Students in Computer Programming Courses: A Mixed-Method ApproachFebruary 2026 · Discover Education 2026
- Human-Robo-advisor collaboration in decision-making: Evidence from a multiphase mixed methods experimental studyOctober 2, 2025 · Decision Support Systems 2025
- Human-AI Collaboration in Software Development: A Mixed-Methods Study of Developers' Use of GitHub Copilot and ChatGPT2025 · FSE Companion 2025
- Examining University Students' Engagement with ChatGPT in English Essay Writing: Interaction Patterns and Perceptions2026 · The Asia-Pacific Education Researcher 2026
- Enhancing School Students' Self-Regulated Learning through Generative AI Support: A Randomized Controlled Trial2026 · Educational Psychology Review 2026
- SWE-chat: Coding Agent Interactions From Real Users in the WildApril 22, 2026 · arXiv