English

Agentic Workflow for Education: Concepts and Applications

Computers and Society 2025-09-03 v1 Artificial Intelligence Emerging Technologies

Abstract

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.

Keywords

Cite

@article{arxiv.2509.01517,
  title  = {Agentic Workflow for Education: Concepts and Applications},
  author = {Yuan-Hao Jiang and Yijie Lu and Ling Dai and Jiatong Wang and Ruijia Li and Bo Jiang},
  journal= {arXiv preprint arXiv:2509.01517},
  year   = {2025}
}

Comments

Proceedings of the 33rd International Conference on Computers in Education (ICCE 2025). Asia-Pacific Society for Computers in Education

R2 v1 2026-07-01T05:15:30.858Z