EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CalcTutor: Multi-Agent LLM Grading of Handwritten Mathematics with RAG-Grounded Feedback for Adaptive Learning Support

Le Ying Tan, Buyuan Zhu, Shiyu Hu, Ankit Mishra, Darren J. Yeo, Kang Hao Cheong

Mathematics · 24.03.2026 · 14 (7) · 1094

DOI: 10.3390/math14071094 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 24.03.2026. Verfasst von Le Ying Tan und 5 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Singapore Ministry of Education (MOE) Tertiary Education Research Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Personalized instruction remains a major bottleneck in higher education, especially in large classes where timely, individualized feedback is difficult to achieve. Existing automation typically relies on rigid rule-based pipelines or computationally heavy deep learning models, making it difficult to simultaneously achieve interpretability, instructional usability, and scalable deployment. In this study, we present CalcTutor, a generative-AI-based assessment and feedback system designed to support open-ended handwritten calculus problem solving. The system organizes instructional support through three coordinated components: (1) a multi-agent large language model (LLM) mechanism that evaluates solution processes and produces diagnostic feedback, (2) a retrieval-augmented generation (RAG) pipeline that links diagnosed difficulties to aligned instructional materials, and (3) real-time learner analytics for both students and instructors, forming an integrated instructional support workflow rather than an automated answer-checking tool. In offline evaluation and a pilot classroom deployment, the multi-agent grader achieved a weighted agreement accuracy of 0.931 and an F1-score of 0.934 on 1055 handwritten solutions. Participant feedback and workflow testing indicated that CalcTutor can be stably integrated into routine classroom use and enables students to interpret and act upon the provided feedback. These results indicate that automated assessment, diagnostic feedback, and targeted review can operate coherently within a single instructional process that supports instructor-led assessment practices. Using undergraduate calculus as an application domain for open-ended handwritten mathematical assessment, the study demonstrates the operational feasibility of a closed-loop assessment–feedback–revision workflow and provides a deployable instructional infrastructure for formative instructional support in real classroom contexts.

Förderung

  • Singapore Ministry of Education (MOE) Tertiary Education Research Fund

Zitieren

APA

Tan, L. Y., Zhu, B., Hu, S., Mishra, A., Yeo, D. J., & Cheong, K. H. (2026). CalcTutor: Multi-Agent LLM Grading of Handwritten Mathematics with RAG-Grounded Feedback for Adaptive Learning Support. Mathematics, 14(7), 1094. https://doi.org/10.3390/math14071094

Vancouver

Tan LY, Zhu B, Hu S, Mishra A, Yeo DJ, Cheong KH. CalcTutor: Multi-Agent LLM Grading of Handwritten Mathematics with RAG-Grounded Feedback for Adaptive Learning Support. Mathematics. 2026;14(7):1094. doi:10.3390/math14071094

BibTeX
@article{Tan2026,
  author = {Tan, Le Ying and Zhu, Buyuan and Hu, Shiyu and Mishra, Ankit and Yeo, Darren J. and Cheong, Kang Hao},
  title = {CalcTutor: Multi-Agent LLM Grading of Handwritten Mathematics with RAG-Grounded Feedback for Adaptive Learning Support},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {7},
  pages = {1094},
  doi = {10.3390/math14071094}
}
Kostenlos starten →