Developing an LLM-Based Feedback System Grounded in Evidence-Centered Design to Support Physics Problem Solving

arXiv:2512.10785 · physics.ed-ph, cs.AI, cs.HC · Submitted 2025-12-11 · Read on arXiv

physics.ed-ph, cs.AI, cs.HC

Submitted: 2025-12-11

Updated: 2026-07-06

Terminology

• Generative AI — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes

Related papers

• Using Learning Analytics to Study Novice Learners' Work on Quantum Circuit Simulator Tasks
• LLM-as-a-judge validity is strongly task-dependent across physics assessment formats
• Artificial Neural Network Assisted Modelling of Tangent Galvanometer Measurements for the Determination of Horizontal Component of Earth's Magnetic Field