LLM-Augmented Real-Time Assessment and Personalized Feedback in Instructional Systems

Tianlun Yang; Zuyao Wang; Anhai Yao; Georgios Kapogiannis; Byung-Gyoo Kang

doi:10.2991/978-2-38476-569-0_10

<Previous Article In Volume

Next Article In Volume>

LLM-Augmented Real-Time Assessment and Personalized Feedback in Instructional Systems

Authors

Tianlun Yang¹^{, *}, Zuyao Wang¹, Anhai Yao², Georgios Kapogiannis³, Byung-Gyoo Kang⁴

¹NingboTech University, Ningbo, ZJ, 315100, China

²Zhejiang Sci-Tech University, Hangzhou, ZJ, 310018, China

³University of Warwick, Coventry, CV4 7AL, UK

⁴University of Nottingham Ningbo China, Ningbo, ZJ, 315100, China

^*Corresponding author. Email: tianlun.yang@nbt.edu.cn

Corresponding Author

Tianlun Yang

Available Online 1 May 2026.

DOI: 10.2991/978-2-38476-569-0_10 How to use a DOI?
Keywords: LLM; Real-Time Feedback; Intelligent Instructional System
Abstract: This study confronts the latency and generic nature of conventional pedagogical feedback by architecting and deploying an LLM-driven intelligent instructional system. Following a literature review of extant scholarship, this study first delineated the technical affordances that enable deep integration of large language models with educational contexts. This study then engineered a production-ready B/S architecture in which a lightweight front end orchestrates learner interaction while a scalable back end securely queries the model’s official API to perform real-time semantic parsing and adaptive feedback synthesis. The system’s kernel is a personalized, real-time feedback loop that continuously calibrates instructional scaffolds to individual cognitive profiles. Empirical assessment within authentic classroom settings demonstrates the system’s instructional efficacy.
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume

Next Article In Volume>

Volume Title: Proceedings of the 3rd International Conference on Educational Development and Social Sciences (EDSS 2026)
Series: Advances in Social Science, Education and Humanities Research
Publication Date: 1 May 2026
ISBN: 978-2-38476-569-0
ISSN: 2352-5398
DOI: 10.2991/978-2-38476-569-0_10 How to use a DOI?
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

ris enw bib

TY  - CONF
AU  - Tianlun Yang
AU  - Zuyao Wang
AU  - Anhai Yao
AU  - Georgios Kapogiannis
AU  - Byung-Gyoo Kang
PY  - 2026
DA  - 2026/05/01
TI  - LLM-Augmented Real-Time Assessment and Personalized Feedback in Instructional Systems
BT  - Proceedings of the 3rd International Conference on Educational Development and Social Sciences (EDSS 2026)
PB  - Atlantis Press
SP  - 73
EP  - 83
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-569-0_10
DO  - 10.2991/978-2-38476-569-0_10
ID  - Yang2026
ER  -

download .riscopy to clipboard