Intelligent Error Management Empowered by Large Language Model-based Agent in EFL Education of Junior High

DOI

10.2991/978-2-38476-577-5_48How to use a DOI?

Keywords

LLM-based agent; intelligent English error management; plugin-augmented; workflow-driven

Abstract

This study examines the implementation pathways of large language model (LLM)-based agent for English error management in EFL education, comparing two LLM-based agent systems: a plugin-augmented agent (EEM_PA) and a structured workflow-driven agent (EEM_WF). Both systems were developed using the DeepSeek model and deployed on the low-code agent configuration platform COZE. Through a comparative evaluation focused on functional performance and user experience among ten Chinese junior high students with similar English proficiency, the study found that while both systems demonstrated comparable functional effectiveness, the plugin-augmented EEM_PA outperformed the workflow-driven EEM_WF in terms of user experience. This suggests that the workflow-driven design, though systematic and potentially useful for standardized review, may function more as a supportive tool for teachers or parents rather than as an engaging learning companion for students. This study highlights practical pathways for educators to develop intelligent tutoring systems by leveraging LLMs and low-code platforms. It offers a comparative reference for designing AI-assisted learning tools that balance interactive engagement with structured pedagogical support.

Copyright

© 2026 The Author(s)

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)

TY  - CONF
AU  - Jiahui Hou
AU  - Yingchun Ren
PY  - 2026
DA  - 2026/05/15
TI  - Intelligent Error Management Empowered by Large Language Model-based Agent in EFL Education of Junior High
BT  - Proceedings of the 2026 5th International Conference on Social Sciences and Humanities and Arts (SSHA 2026)
PB  - Atlantis Press
SP  - 463
EP  - 471
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-577-5_48
DO  - 10.2991/978-2-38476-577-5_48
ID  - Hou2026
ER  -