Balancing Game Satisfaction and Resource Efficiency: LLM and Pursuit Learning Automata for NPC Dialogues

Enhancing the dialogue interactions of Non-Player Characters (NPCs) in video games, this work introduces a novel integration of Large Language Models (LLMs) with Pursuit Learning Automata (PLA). The approach is designed to foster dynamic, engaging, and contextually relevant conversations within a highly resource-efficient framework. Utilizing the generative strengths of LLMs alongside the adaptive learning properties of PLA, the system presented here dynamically modulates dialogue tones and emotions. This ensures a tailored gaming experience that does not require online LLM processing. Initial findings suggest that this method boosts player engagement and satisfaction, contributing to the development of more immersive and responsive gaming worlds.