An Adaptive AI Framework for Student Domain and Career Guidance

Abstract

Choosing an appropriate academic stream and career path is a complex decision for students due to the wide range of educational and professional opportunities available today. This paper proposes an Adaptive AI Framework for Student Domain and Career Guidance that supports personalized academic and career recommendations based on students' interests, aptitude, preferences, and cognitive abilities. The framework operates through three stages: student profiling and assessment, academic stream classification, and domain-specific recommendation generation. A structured questionnaire and weighted scoring mechanism are used to evaluate student responses and identify suitable academic domains. In addition, a domain-specific keyword repository is incorporated to improve recommendation relevance. The framework also outlines the future integration of Small Language Models (SLMs), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) to enable adaptive questioning and more personalized assessments. The proposed approach provides an intelligent and scalable decision-support system that can assist students and career counselors in making informed academic and professional choices.