Problem
Research questions and friction points this paper is trying to address.
Intelligent Tutoring Systems
Cognitive State Regulation
Adaptive Feedback
Student Learning Behaviors
Closed-loop Learning
TutorLoop: Regulating Student Learning Behaviors via Sensor-in-the-Loop Generative Feedback
🤖 AI Summary
This work addresses the limitations of conventional LLM-based tutoring systems, which typically rely on scenario-specific content and employ myopic feedback mapping. We propose a learning behavior regulation framework grounded in real-time cognitive state estimation. The system captures signals via camera in a closed loop and leverages deep reinforcement learning (DRL) to overcome direct mapping bottlenecks, thereby globally optimizing feedback strategies. A large language model is further integrated to generate humanized instructional guidance, enabling adaptive human–machine collaborative teaching. A user study involving 187 participants demonstrates that the proposed system delivers more precise interventions, significantly enhancing learner attention and engagement while effectively reducing cognitive load and improving overall learning outcomes.
📝 Abstract
We present TutorLoop, a sensor-in-the-loop system that regulates student learning behaviors by delivering adaptive feedback based on real-time cognitive states. Unlike prior large language model (LLM) tutors that directly depend on scenario-specific content, TutorLoop operates on sensor-derived signals captured via webcams. Moreover, unlike direct cognitive-to-feedback mappings that are short-sighted, the system employs a deep reinforcement learning (DRL) agent to optimize the feedback type across the entire learning process. Finally, another LLM tutor refines feedback into human-like, context-aware messages. We evaluate TutorLoop in a large-scale user study (N=187), where a model trained offline is directly applied to a new learning task without retraining. Results show that TutorLoop provides less frequent yet more effective interventions, improving attention, reducing workload, increasing engagement, and ultimately enhancing learning outcomes. These findings highlight the potential of closed-loop, sensor-driven feedback for scalable human-AI integrated systems to support learning.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Sensor-in-the-Loop
Deep Reinforcement Learning
Large Language Model
Adaptive Feedback
Cognitive State
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
