A Context-Aware Retrieval-Augmented Generation Framework for Personalized Learning and Automated Course Development

The rapid growth of digital learning resources has created both opportunity and overload for learners navigating online education. This paper presents EDURAG, an AI-powered personalized learning and course generation platform that combines generative artificial intelligence with retrieval-augmented generation (RAG) to deliver adaptive, context-aware educational experiences. EDURAG integrates secure user authentication, a personalized analytics dashboard, automated course generation, structured lesson management, progress tracking, and a conversational AI teacher grounded in a curated knowledge base. The platform is built on a modern full-stack architecture using Next.js, React, and Tailwind CSS on the client and application layer, with Prisma ORM and SQLite for structured data persistence, and JWT/Jose-based authentication secured by bcrypt password hashing. This paper describes the motivation, system architecture, implementation, and functional modules of EDURAG, and situates the platform within the broader literature on intelligent tutoring systems, adaptive learning, and retrieval-augmented generation. We discuss how the fusion of generative and retrieval-based methods mitigates hallucination and improves factual grounding in AI tutoring responses, while also examining limitations such as data quality dependency, domain coverage, and the ethical considerations inherent in AI-mediated education. The paper concludes that EDURAG demonstrates a practical, extensible architecture for trustworthy, personalized AI-driven learning and outlines directions for future research and development.

Authors

Institutions

Publication Details

Journal
International Journal of Scientific Research in Science Engineering and Technology
Published
2026-11-16
DOI
https://doi.org/10.32628/ijsrset261364
Primary Topic
Intelligent Tutoring Systems and Adaptive Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Context-Aware Retrieval-Augmented Generation Framework for Personalized Learning and Automated Course Development

Yusuf Perwej, Atharv Vats Singh, Sushmita Singh, Manasi Singh et al.
3 links
International Journal of Scientific Research in Science Engineering and Technology
Intelligent Tutoring Systems and Adaptive Learning
article

A Context-Aware Retrieval-Augmented Generation Framework for Personalized Learning and Automated Course Development

Yusuf Perwej, Atharv Vats Singh, Sushmita Singh, Manasi Singh, Aditya Raj
article en

Abstract

The rapid growth of digital learning resources has created both opportunity and overload for learners navigating online education. This paper presents EDURAG, an AI-powered personalized learning and course generation platform that combines generative artificial intelligence with retrieval-augmented generation (RAG) to deliver adaptive, context-aware educational experiences. EDURAG integrates secure user authentication, a personalized analytics dashboard, automated course generation, structured lesson management, progress tracking, and a conversational AI teacher grounded in a curated knowledge base. The platform is built on a modern full-stack architecture using Next.js, React, and Tailwind CSS on the client and application layer, with Prisma ORM and SQLite for structured data persistence, and JWT/Jose-based authentication secured by bcrypt password hashing. This paper describes the motivation, system architecture, implementation, and functional modules of EDURAG, and situates the platform within the broader literature on intelligent tutoring systems, adaptive learning, and retrieval-augmented generation. We discuss how the fusion of generative and retrieval-based methods mitigates hallucination and improves factual grounding in AI tutoring responses, while also examining limitations such as data quality dependency, domain coverage, and the ethical considerations inherent in AI-mediated education. The paper concludes that EDURAG demonstrates a practical, extensible architecture for trustworthy, personalized AI-driven learning and outlines directions for future research and development.

International Journal of Scientific Research in Science Engineering and TechnologyVol. 13(6)
Shri Ramswaroop Memorial University (IN)
Quality education
Intelligent Tutoring Systems and Adaptive Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon