CyberJustice Tutor: An Agentic AI Framework for Cybersecurity Learning via Think-Plan-Act Reasoning and Pedagogical Scaffolding

2026-03-19

AI Summary

This study addresses the limitations of traditional reactive chatbots in cybersecurity education for criminal justice professionals, which often generate hallucinations in high-stakes legal contexts due to inadequate state modeling. To overcome this, the authors propose an agent-based AI educational dialogue system that innovatively integrates a “think–plan–act” cognitive loop, adaptive retrieval-augmented generation (RAG), and Vygotsky’s Zone of Proximal Development (ZPD) theory to construct a dynamic instructional scaffolding mechanism. This framework enables goal decomposition, contextual tracking, and personalized learning path generation. Evaluated with 123 law enforcement officers, students, and educators, the system demonstrated strong performance in response speed (4.7/5), usability (4.4/5), and accuracy (4.3/5), confirming its effectiveness and reliability in specialized legal cybersecurity education.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent Communication
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The integration of Large Language Models (LLMs) into cybersecurity education for criminal justice professionals is currently hindered by the "statelessness" of reactive chatbots and the risk of hallucinations in high-stakes legal contexts. To address these limitations, we propose the CyberJustice Tutor, an educational dialogue system powered by an Agentic AI framework. Unlike reactive chatbots, our system employs a "Think-Plan-Act" cognitive cycle, enabling autonomous goal decomposition, longitudinal planning, and dynamic context maintenance. We integrate a Pedagogical Scaffolding Layer grounded in Vygotsky's Zone of Proximal Development (ZPD), which dynamically adapts instructional support based on the learner's real-time progress. Furthermore, an Adaptive Retrieval Augmented Generation (RAG) core anchors the agent's reasoning in verified curriculum materials to ensure legal and technical accuracy. A comprehensive user study with 123 participants, including students, educators, and active law enforcement officers, validated the system's efficacy. Quantitative results demonstrate high user acceptance for Response Speed (4.7/5), Ease of Use (4.4/5), and Accuracy (4.3/5). Qualitative feedback indicates that the agentic architecture is perceived as highly effective in guiding learners through personalized paths, demonstrating the feasibility and usability of agentic AI for specialized professional education.

Problem

• statelessness
• hallucinations
• cybersecurity education
• criminal justice professionals
• Large Language Models

Innovation

• Agentic AI
• Think-Plan-Act Reasoning
• Pedagogical Scaffolding
• Adaptive RAG
• Cybersecurity Education