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

TL;DR

This paper introduces AUSS, a multi-agent AI framework for education that integrates personalization, automation, and institutional intelligence, leveraging LLMs and analytics to improve educational outcomes.

Contribution

It presents a novel multi-agent architecture that unifies personalized learning, educator support, and institutional insights using advanced AI techniques.

Findings

Recommendation accuracy improved to 92.4%

Grading efficiency increased by 94.1%

Dropout prediction F1-score reached 89.5%

Abstract

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.