Agentic Workflow for Education: Concepts and Applications
This addresses the problem of inefficient and non-scalable educational systems for educators and learners, but it appears incremental as it builds on existing LLM and agent technologies.
This study tackles the problem of static, linear interactions in education by introducing the Agentic Workflow for Education (AWE), a four-component model that enables dynamic, nonlinear workflows, resulting in AWE-generated math test items being statistically comparable to real exam questions.
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.