A Framework for Adaptive Game Play and Adversary Creation Based on Gamer Behavioral Analysis and Large Language (LLM) Models

As the gaming industry undergoes rapid expansion, the need to enhance player engagement and adaptability within games is paramount. By leveraging behavioral analytics derived from player interactions, this study proposes a framework for recommending adaptive game play adjustments, such as altering narrative elements or modifying enemy types needed to sustain player interest. The implementation of the LLM (Large Language Models) framework facilitates the generation of detailed recommendations, aiding game designers in the refinement process. This paper presents a comprehensive literature review of current relevant research. In addition, we suggest the structure of the framework to be utilized, serving as a foundational structure for future enhancements and iterations. Suggestions of platforms to be used in implementing the framework are also referenced.