Score: 0

Agentic Workflow for Education: Concepts and Applications

Published: September 1, 2025 | arXiv ID: 2509.01517v1

By: Yuan-Hao Jiang , Yijie Lu , Ling Dai and more

Potential Business Impact:

AI helps teachers make better, personalized lessons.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

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.

Country of Origin
🇨🇳 China

Page Count
10 pages

Category
Computer Science:
Computers and Society