Beyond Answers: Large Language Model-Powered Tutoring System in Physics Education for Deep Learning and Precise Understanding
Abstract
This paper proposes Physics-STAR, a framework for large language model (LLM)-powered tutoring system designed to provide personalized and adaptive learning experiences for high school students. Results showed that Physics-STAR increased students' average scores and efficiency on conceptual, computational, and informational questions. Students' average scores on complex information problems increased by 100% and their efficiency increased by 5.95%.
Used in syntheses
Questions this source addresses
- How does the timing of practice change what we remember?
- When does mixing different kinds of practice help us learn?
- When should an intelligent tutor make learning harder?
- Why do some things we learn stay with us?
- How does Physics-STAR use step-by-step guidance and reflective prompts instead of direct answers to support deeper learning in high school physics?
- How does personalized, adaptive difficulty adjustment in an LLM tutoring system align with worked-example and guidance-fading principles from cognitive load theory?
- What gains in accuracy and efficiency did students show on conceptual, computational, and informational physics questions after using Physics-STAR?
- Why did complex information problems see a 100% score improvement while overall efficiency gains were more modest at 5.95%?