The primary goal of this study is to analyze agentic workflows in education according to the proposed four major technological paradigms: reflection, planning, tool use, and multi-agent collaboration. We critically examine the role of AI agents in education through these key design paradigms, exploring their advantages, applications, and challenges. Second, to illustrate the practical potential of agentic systems, we present a proof-of-concept application: a multi-agent framework for automated essay scoring. Preliminary results suggest this agentic approach may offer improved consistency compared to stand-alone LLMs. Our findings highlight the transformative potential of AI agents in educational settings while underscoring the need for further research into their interpretability and trustworthiness.
@article{arxiv.2504.20082,
title = {Evolution of AI in Education: Agentic Workflows},
author = {Firuz Kamalov and David Santandreu Calonge and Linda Smail and Dilshod Azizov and Dimple R. Thadani and Theresa Kwong and Amara Atif},
journal= {arXiv preprint arXiv:2504.20082},
year = {2026}
}
Comments
made the abstract more succinct, revised the methodology, added PRISMA flow chart, updated references