Agentic Workflow for Education: Concepts and Applications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Yuan-Hao, Lu, Yijie, Dai, Ling, Wang, Jiatong, Li, Ruijia, Jiang, Bo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908514437300224
author Jiang, Yuan-Hao
Lu, Yijie
Dai, Ling
Wang, Jiatong
Li, Ruijia
Jiang, Bo
author_facet Jiang, Yuan-Hao
Lu, Yijie
Dai, Ling
Wang, Jiatong
Li, Ruijia
Jiang, Bo
contents With the rapid advancement of Large Language Models (LLMs) and Artificial Intelligence (AI) agents, agentic workflows are showing transformative potential in education. This study introduces the Agentic Workflow for Education (AWE), a four-component model comprising self-reflection, tool invocation, task planning, and multi-agent collaboration. We distinguish AWE from traditional LLM-based linear interactions and propose a theoretical framework grounded in the von Neumann Multi-Agent System (MAS) architecture. Through a paradigm shift from static prompt-response systems to dynamic, nonlinear workflows, AWE enables scalable, personalized, and collaborative task execution. We further identify four core application domains: integrated learning environments, personalized AI-assisted learning, simulation-based experimentation, and data-driven decision-making. A case study on automated math test generation shows that AWE-generated items are statistically comparable to real exam questions, validating the model's effectiveness. AWE offers a promising path toward reducing teacher workload, enhancing instructional quality, and enabling broader educational innovation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_01517
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Agentic Workflow for Education: Concepts and Applications
Jiang, Yuan-Hao
Lu, Yijie
Dai, Ling
Wang, Jiatong
Li, Ruijia
Jiang, Bo
Computers and Society
Artificial Intelligence
Emerging Technologies
With the rapid advancement of Large Language Models (LLMs) and Artificial Intelligence (AI) agents, agentic workflows are showing transformative potential in education. This study introduces the Agentic Workflow for Education (AWE), a four-component model comprising self-reflection, tool invocation, task planning, and multi-agent collaboration. We distinguish AWE from traditional LLM-based linear interactions and propose a theoretical framework grounded in the von Neumann Multi-Agent System (MAS) architecture. Through a paradigm shift from static prompt-response systems to dynamic, nonlinear workflows, AWE enables scalable, personalized, and collaborative task execution. We further identify four core application domains: integrated learning environments, personalized AI-assisted learning, simulation-based experimentation, and data-driven decision-making. A case study on automated math test generation shows that AWE-generated items are statistically comparable to real exam questions, validating the model's effectiveness. AWE offers a promising path toward reducing teacher workload, enhancing instructional quality, and enabling broader educational innovation.
title Agentic Workflow for Education: Concepts and Applications
topic Computers and Society
Artificial Intelligence
Emerging Technologies
url https://arxiv.org/abs/2509.01517