EUVIMEDEUVIMED entdecken
Crossref

A Virtual Tutoring System Based on Large Language Models for Engineering Mathematics Education: A Proof‐of‐Concept Study

Manoel de Pontes Fernandes, Adriel Ferreira Trajano, Alisson Vasconcelos de Brito, José Augusto da Silva Barbosa, Moisés Dantas dos Santos, Thiago José Machado

Computer Applications in Engineering Education · 2026-11 · 34 (6)

DOI: 10.1002/cae.70290 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Applications in Engineering Education, online erschienen am 06.11.2026. Verfasst von Manoel de Pontes Fernandes und 5 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Engineering education relies heavily on students' ability to apply mathematical reasoning to model, analyze, and solve complex problems across multiple domains. However, persistent difficulties in foundational mathematics courses remain a major challenge in undergraduate engineering programs, particularly in contexts marked by socioeconomic disparities. In this study, we present V‐MATH, a virtual tutoring system powered by large language models (LLMs) and designed to support engineering mathematics learning through a structured, computational, and pedagogically grounded approach. The system integrates optical character recognition for problem input validation, LaTeX‐based solution formatting, and WhatsApp‐based delivery to enhance accessibility, usability, and scalability. The architecture also incorporates retrieval‐augmented generation (RAG), auxiliary multi‐agent verification mechanisms, and graphical generation modules designed to improve mathematical consistency, reduce hallucinations, and support engineering‐oriented visualization tasks. Its instructional logic operationalizes Pólya's problem‐solving framework to provide step‐by‐step explanations aligned with engineering problem‐solving practices. The present work is explicitly framed as a proof of concept evaluated in a controlled, non‐classroom setting. Preliminary evaluations using items from national examinations (ENEM and ENA), employed as benchmarks of mathematical competencies relevant to engineering education, indicate that V‐MATH achieves accuracy above 90%, outperforming general‐purpose LLMs while offering greater pedagogical transparency. Given that V‐MATH is a complete workflow, rather than merely an isolated language model, this comparison should be interpreted as a system‐level contrast rather than a model‐level one, and the evidence presented here demonstrates the technical feasibility and pedagogically informed structuring of the proposed system. Overall, the findings suggest that V‐MATH represents a promising direction for the development of pedagogically grounded, multimodal, and reliability‐oriented AI tutoring systems for engineering education, motivating future validation in engineering classrooms.

Zitieren

APA

Fernandes, M. D. P., Trajano, A. F., Brito, A. V. D., Barbosa, J. A. D. S., Santos, M. D. D., & Machado, T. J. (2026). A Virtual Tutoring System Based on Large Language Models for Engineering Mathematics Education: A Proof‐of‐Concept Study. Computer Applications in Engineering Education, 34(6). https://doi.org/10.1002/cae.70290

Vancouver

Fernandes MDP, Trajano AF, Brito AVD, Barbosa JADS, Santos MDD, Machado TJ. A Virtual Tutoring System Based on Large Language Models for Engineering Mathematics Education: A Proof‐of‐Concept Study. Computer Applications in Engineering Education. 2026;34(6). doi:10.1002/cae.70290

BibTeX
@article{Fernandes2026,
  author = {Fernandes, Manoel de Pontes and Trajano, Adriel Ferreira and Brito, Alisson Vasconcelos de and Barbosa, José Augusto da Silva and Santos, Moisés Dantas dos and Machado, Thiago José},
  title = {A Virtual Tutoring System Based on Large Language Models for Engineering Mathematics Education: A Proof‐of‐Concept Study},
  journal = {Computer Applications in Engineering Education},
  year = {2026},
  volume = {34},
  number = {6},
  doi = {10.1002/cae.70290}
}
Kostenlos starten →