---
source_url: https://arxiv.org/abs/2504.20082v2
ingested: 2026-05-07
sha256: d7f7e3d98f3e4397dd4894c8b3d057ca99f7882147fd9a4a958c23951fc13c8f
---
# Evolution of AI in Education: Agentic Workflows

**Authors:** Firuz Kamalov, David Santandreu Calonge, Linda Smail, Dilshod Azizov, Dimple R. Thadani, Theresa Kwong, Amara Atif  
**arXiv:** 2504.20082v2  
**Submitted:** 25 Apr 2025 | Revised: 26 Jan 2026  

## Abstract

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.

## Key Contributions

- **Four Proposed Paradigms** for agentic workflows in education:
  1. Reflection
  2. Planning
  3. Tool use
  4. Multi-agent collaboration
- **Critical Analysis** of AI agents' advantages, applications, and challenges through these design paradigms.
- **Proof-of-Concept**: Multi-agent framework for automated essay scoring.
- **Preliminary Finding**: Agentic systems may deliver improved consistency versus stand-alone LLMs.
- **Identified Gaps**: Need for further research into interpretability and trustworthiness of educational AI agents.