Planned enhancements: multi-turn conversational follow-up, RAG-based personalization, and feedback analytics for AI-assisted instruction¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The authors outline future iterations of the instructional assistant: interactive or multi-turn LLM feedback so students can ask follow-up questions simulating a conversational tutoring experience; Retrieval-Augmented Generation (RAG) pipelines to tailor explanations to each student's feedback history and the course's exact terminology; sentiment analysis of feedback; and personalization of the output's tone, depth, or format based on individual learner preferences. These are stated plans, not evaluated features.

Design Implications¶

Context¶

Requirements¶

• A deployed LLM-assisted instruction system already collecting student feedback

Constraints¶

• None of these enhancements has been evaluated in the present study; they are described as plans

Target Learners¶

• university students in cybersecurity and, planned, courses beyond cybersecurity

Target Learning Goals¶

• personalized, conversational clarification of instructional content aligned with course terminology

Related Strategies¶

• Future improvements: real-world user studies, advanced student modeling, and spaced repetition
• Iterative semester-long improvement cycles combining feature integration with real-world testing
• Upgrade retrieval to Agentic RAG and adopt context-aware emotive narration to reduce cognitive load

Examples¶

-

Key Sources¶

• Patel, K., Lin, Y.-Z., Raul, G., Shih, B. P.-J., Redondo, M. W., Latibari, B. S., Pacheco, J., Salehi, S., & Satam, P. (2025). Integrating Generative AI into Cybersecurity Education: A Study of OCR and Multimodal LLM-assisted Instruction. arXiv. https://arxiv.org/abs/2509.02998. doi:10.48550/arxiv.2509.02998