abstract
- This paper presents a state-of-the-art review analyzing the integration of Large Language Models (LLMs), Knowledge Graphs (KGs), and Reinforcement Learning (RL) in decision-making systems. We evaluate methodologies that enhance predictive accuracy and contextual coherence. Our findings support a hybrid KG-RL framework to improve performance through adaptable learning. This review synthesizes insights from 72 articles, providing a foundation for future research in this interdisciplinary field. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.