AI-Enhanced Assignment Grading in Higher Education
International Journal of Web Services Research · 29.10.2026 · 23 (1) · 1-17
DOI: 10.4018/ijwsr.426139 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Web Services Research, erschienen am 29.10.2026. Verfasst von Yi Li und 2 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).
Abstract (Originalsprache)
The digitalization of education is critical for educational modernization and equitable access to quality education. However, higher education institutions face significant challenges in homework grading due to large student enrollments, including low grading efficiency and insufficient personalized feedback. This paper presents a general multi-agent framework leveraging large language models for automated assignment grading in higher education. The framework employed seven specialized agents: document reader, format converter, parser, artificial intelligence grading, data aggregation, report generation, and error handling. This domain-agnostic framework can be adapted to various disciplines by configuring appropriate grading criteria. A case study across nine classes with 258 students demonstrated 14–39 times efficiency improvement, reducing single-class processing time from 32–63 minutes to 1.6–2.3 minutes. The results indicated that the approach significantly reduced teachers' workload while providing targeted feedback, advancing digital transformation in education.
Zitieren
APA
Li, Y., Lin, X., & Zhang, Y. (2026). AI-Enhanced Assignment Grading in Higher Education. International Journal of Web Services Research, 23(1), 1-17. https://doi.org/10.4018/ijwsr.426139
Vancouver
Li Y, Lin X, Zhang Y. AI-Enhanced Assignment Grading in Higher Education. International Journal of Web Services Research. 2026;23(1):1-17. doi:10.4018/ijwsr.426139
BibTeX
@article{Li2026,
author = {Li, Yi and Lin, Xingyu and Zhang, Yue},
title = {AI-Enhanced Assignment Grading in Higher Education},
journal = {International Journal of Web Services Research},
year = {2026},
volume = {23},
number = {1},
pages = {1--17},
doi = {10.4018/ijwsr.426139}
}
EUVIMED