• Bhakti Ahirwadkar
• Seema Chaudhary

Recommender systems (RS) have evolved from simple collaborative filtering models to sophisticated frameworks powered by large language models (LLMs). This survey reviews the trajectory of research over the past three decades, focusing on the shift from classical recommendation paradigms to deep learning and recent LLM-based methods. We classify the literature into six stages: early collaborative and content-based filtering, hybrid and ensemble models, context-aware systems, deep learning-based recommender systems, explainable recommendation, and the emergence of LLM-powered systems. Key milestones, representative approaches, and open challenges are highlighted, providing a comprehensive overview for researchers and practitioners.

Recommender System, Large Language Model (LLM), Prompt Engineering, LLM Augmented RS, Deep Neural Network, CNN, Autoencoder, RNN

"Survey on the Evolution of Recommender Systems: From Classical Models to LLM-based Approaches", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 10, page no.a286-a290, October-2025, Available :http://www.jetir.org/papers/JETIR2510034.pdf

"Survey on the Evolution of Recommender Systems: From Classical Models to LLM-based Approaches", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 10, page no. ppa286-a290, October-2025, Available at : http://www.jetir.org/papers/JETIR2510034.pdf