Learner and Instructor Needs in AI-Supported Programming Learning Tools: Design Implications for Features and Adaptive Control

2025-02-28

AI Summary

This study addresses the tension between learner autonomy and instructor authority in AI-powered programming learning tools. Through participatory design (15 students, 10 instructors), semi-structured interviews, and a large-scale survey (172 students), it identifies divergent needs: novices prioritize encouraging feedback, visual scaffolding, peer references, progress awareness, and best-practice reinforcement, whereas instructors emphasize pedagogical alignment and intervention efficacy. The work introduces, for the first time, a “shared control” framework featuring role-specific adaptive mechanisms that dynamically balance learner autonomy with instructor-guided scaffolding, and identifies key determinants of individual control preferences. It delivers actionable, empirically grounded design guidelines for AI-enhanced educational tools—supporting adaptive systems that are motivating, interpretable, and pedagogically coherent—thereby significantly improving novice programming persistence and instructor intervention effectiveness.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Intelligent Robots: Behavior Learning & Control
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

AI-supported tools can help learners overcome challenges in programming education by providing adaptive assistance. However, existing research often focuses on individual tools rather than deriving broader design recommendations. A key challenge in designing these systems is balancing learner control with system-driven guidance. To explore user preferences for AI-supported programming learning tools, we conducted a participatory design study with 15 undergraduate novice programmers and 10 instructors to gather insights on their desired help features and control preferences, as well as a follow-up survey with 172 introductory programming students. Our qualitative findings show that learners prefer help that is encouraging, incorporates visual aids, and includes peer-related insights, whereas instructors prioritize scaffolding that reflects learners' progress and reinforces best practices. Both groups favor shared control, though learners generally prefer more autonomy, while instructors lean toward greater system guidance to prevent cognitive overload. Additionally, our interviews revealed individual differences in control preferences. Based on our findings, we propose design guidelines for AI-supported programming tools, particularly regarding user-centered help features and adaptive control mechanisms. Our work contributes to the human-centered design of AI-supported learning environments by informing the development of systems that effectively balance autonomy and guidance, enhancing AI-supported educational tools for programming and beyond.

Problem

• Balancing learner control with system-driven guidance in AI-supported programming tools.
• Identifying user preferences for help features and control in programming education.
• Proposing design guidelines for adaptive control and user-centered help features.

Innovation

• Participatory design study with learners and instructors
• User-centered help features with visual aids
• Adaptive control balancing autonomy and guidance