Agentic AI for Education: A Unified Multi-Agent Framework for Personalized Learning and Institutional Intelligence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: J, Arya Mary K, Bhaskar, Deepthy K, S, Sinu T, P, Binu V
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908975248703488
author J, Arya Mary K
Bhaskar, Deepthy K
S, Sinu T
P, Binu V
author_facet J, Arya Mary K
Bhaskar, Deepthy K
S, Sinu T
P, Binu V
contents Agentic Artificial Intelligence (AI) represents a paradigm shift from reactive systems to proactive, autonomous decision making frameworks. Existing AI-based educational systems remain fragmented and lack multi-level integration across stakeholders. This paper proposes the Agentic Unified Student Support System (AUSS), a novel multi-agent architecture integrating student-level personalization, educator-level automation, and institutional-level intelligence. The framework leverages Large Language Models (LLMs), reinforcement learning, predictive analytics, and rule-based reasoning. Experimental results demonstrate improvements in recommendation accuracy (92.4%), grading efficiency (94.1%), and dropout prediction (F1-score: 89.5%). The proposed system enables scalable, adaptive, and intelligent educational ecosystems.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16566
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Agentic AI for Education: A Unified Multi-Agent Framework for Personalized Learning and Institutional Intelligence
J, Arya Mary K
Bhaskar, Deepthy K
S, Sinu T
P, Binu V
Multiagent Systems
Agentic Artificial Intelligence (AI) represents a paradigm shift from reactive systems to proactive, autonomous decision making frameworks. Existing AI-based educational systems remain fragmented and lack multi-level integration across stakeholders. This paper proposes the Agentic Unified Student Support System (AUSS), a novel multi-agent architecture integrating student-level personalization, educator-level automation, and institutional-level intelligence. The framework leverages Large Language Models (LLMs), reinforcement learning, predictive analytics, and rule-based reasoning. Experimental results demonstrate improvements in recommendation accuracy (92.4%), grading efficiency (94.1%), and dropout prediction (F1-score: 89.5%). The proposed system enables scalable, adaptive, and intelligent educational ecosystems.
title Agentic AI for Education: A Unified Multi-Agent Framework for Personalized Learning and Institutional Intelligence
topic Multiagent Systems
url https://arxiv.org/abs/2604.16566