LLM Agents for Education: Advances and Applications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chu, Zhendong, Wang, Shen, Xie, Jian, Zhu, Tinghui, Yan, Yibo, Ye, Jinheng, Zhong, Aoxiao, Hu, Xuming, Liang, Jing, Yu, Philip S., Wen, Qingsong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914305186725888
author Chu, Zhendong
Wang, Shen
Xie, Jian
Zhu, Tinghui
Yan, Yibo
Ye, Jinheng
Zhong, Aoxiao
Hu, Xuming
Liang, Jing
Yu, Philip S.
Wen, Qingsong
author_facet Chu, Zhendong
Wang, Shen
Xie, Jian
Zhu, Tinghui
Yan, Yibo
Ye, Jinheng
Zhong, Aoxiao
Hu, Xuming
Liang, Jing
Yu, Philip S.
Wen, Qingsong
contents Large Language Model (LLM) agents are transforming education by automating complex pedagogical tasks and enhancing both teaching and learning processes. In this survey, we present a systematic review of recent advances in applying LLM agents to address key challenges in educational settings, such as feedback comment generation, curriculum design, etc. We analyze the technologies enabling these agents, including representative datasets, benchmarks, and algorithmic frameworks. Additionally, we highlight key challenges in deploying LLM agents in educational settings, including ethical issues, hallucination and overreliance, and integration with existing educational ecosystems. Beyond the core technical focus, we include in Appendix A a comprehensive overview of domain-specific educational agents, covering areas such as science learning, language learning, and professional development.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11733
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM Agents for Education: Advances and Applications
Chu, Zhendong
Wang, Shen
Xie, Jian
Zhu, Tinghui
Yan, Yibo
Ye, Jinheng
Zhong, Aoxiao
Hu, Xuming
Liang, Jing
Yu, Philip S.
Wen, Qingsong
Computers and Society
Artificial Intelligence
Computation and Language
Human-Computer Interaction
Large Language Model (LLM) agents are transforming education by automating complex pedagogical tasks and enhancing both teaching and learning processes. In this survey, we present a systematic review of recent advances in applying LLM agents to address key challenges in educational settings, such as feedback comment generation, curriculum design, etc. We analyze the technologies enabling these agents, including representative datasets, benchmarks, and algorithmic frameworks. Additionally, we highlight key challenges in deploying LLM agents in educational settings, including ethical issues, hallucination and overreliance, and integration with existing educational ecosystems. Beyond the core technical focus, we include in Appendix A a comprehensive overview of domain-specific educational agents, covering areas such as science learning, language learning, and professional development.
title LLM Agents for Education: Advances and Applications
topic Computers and Society
Artificial Intelligence
Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2503.11733