Agentic AI for Education: A Unified Multi-Agent Framework for Personalized Learning and Institutional Intelligence
For educational institutions, it integrates student, educator, and institutional levels into a unified system, but the approach is incremental as it combines existing techniques.
The paper proposes a multi-agent framework (AUSS) for personalized learning and institutional intelligence, achieving 92.4% recommendation accuracy, 94.1% grading efficiency, and 89.5% F1-score for dropout prediction.
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.