Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Baiqiang Wang, Yan Bai, Juan Li

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.

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

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.
Paper Structure (16 sections, 2 figures, 2 tables)

This paper contains 16 sections, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Generative AI and Flipped Learning in Education
  4. The Shift from AI Agents to Agentic AI
  5. Cognitive Architectures: Reasoning and RAG
  6. Pedagogical Scaffolding and Persona Design
  7. Methodology
  8. Agentic AI Framework and Cognitive Planning
  9. Pedagogical Alignment: ZPD and Instructional Scaffolding
  10. System Architecture and Implementation
  11. Experiment Design and Evaluation
  12. Participants and Study Protocol
  13. Results
  14. Quantitative Performance
  15. Qualitative Validation of Methodology
  16. ...and 1 more sections

Figures (2)

  • Figure 1: The architectural workflow of the CyberJustice Tutor. It classifies user intent (Latent Reasoning), generates learning paths or analyzes gaps (Planning), and delivers verified content aligned with the user’s ZPD (Execution)
  • Figure 2: An operational instantiation of the Agentic Tutor Framework. This example illustrates how the system's Planning Module translates a high-level user intent ("Defend against malware") into a structured 5-step curriculum, while the Execution Phase applies high-support scaffolding logic as defined in Table \ref{['tab:scaffolding']}.