ClassAid: A Real-time Instructor-AI-Student Orchestration System for Classroom Programming Activities

2026-02-06

AI Summary

This study addresses the instability of generative AI feedback and the risk of student overreliance in programming education by proposing a teacher-in-the-loop, human-AI collaborative classroom system. The system features a configurable Teaching Assistant Agent (TA Agent) that supports four feedback modes—technical, heuristic, automated, and silent—and integrates an AI-driven real-time visualization dashboard, enabling instructors for the first time to dynamically adjust AI feedback strategies during instruction. Evaluated in an authentic classroom setting with 54 students and one instructor, and supplemented by interviews with eight educators, the results demonstrate that the system significantly enhances the quality of personalized feedback and strengthens teachers’ instructional regulation capabilities, offering a novel paradigm for integrating AI into classroom teaching.

Technology Category

• Humans and AI: Human-in-the-loop Machine Learning
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Intelligent Robots: Embodied AI

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Generative AI is reshaping education, but it also raises concerns about instability and overreliance. In programming classrooms, we aim to leverage its feedback capabilities while reinforcing the educator's role in guiding student-AI interactions. We developed ClassAid, a real-time orchestration system that integrates TA Agents to provide personalized support and an AI-driven dashboard that visualizes student-AI interactions, enabling instructors to dynamically adjust TA Agent modes. Instructors can configure the Agent to provide technical feedback (direct coding solutions), heuristic feedback (hint-based guidance), automatic feedback (autonomously selecting technical or heuristic support), or silent operation (no AI support). We evaluated ClassAid through three aspects: (1) the TA Agents'performance, (2) feedback from 54 students and one instructor during a classroom deployment, and (3) interviews with eight educators. Results demonstrate that dynamic instructor control over AI supports effective real-time personalized feedback and provides design implications for integrating AI into authentic educational settings.

Problem

• Generative AI
• programming education
• instructor control
• student-AI interaction
• overreliance

Innovation

• real-time orchestration
• instructor-controlled AI
• TA Agent
• personalized feedback
• AI dashboard