Answers are grounded in this paper and cite their sources.
As personalized learning gains increasing attention in mathematics education, there is a growing demand for intelligent systems that can assess complex student responses and provide individualized feedback in real time. In this study, we present a personalized auto-grading and feedback system for constructive geometry tasks, developed using large language models (LLMs) and deployed on the Algeomath platform, a Korean online tool designed for interactive geometric constructions. The proposed system evaluates student-submitted geometric constructions by analyzing their procedural accuracy and conceptual understanding. It employs a prompt-based grading mechanism using GPT-4, where student answers and model solutions are compared through a few-shot learning approach. Feedback is generated based on teacher-authored examples built from anticipated student responses, and it dynamically adapts to the student’s problem-solving history, allowing up to four iterative attempts per question. The system was piloted with 79 middle-school students, where LLM-generated grades and feedback were benchmarked against teacher judgments. Grading closely aligned with teachers, and feedback helped many students revise errors and complete multi-step geometry tasks. While short-term corrections were frequent, longer-term transfer effects were less clear. The study reports short-term corrective feedback patterns and attempt-level behaviors observed during classroom use, indicating the system’s role in supporting teacher-aligned formative assessment. The system achieved substantial agreement with teacher scoring, indicating its potential for reliable use in classroom formative assessment.
No takes yet. Share an insight, caveat, or question.
Lee et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: