LLM Reasoner and Automated Planner: A new NPC approach
This addresses the problem of designing plausible NPC behavior in simulations, though it appears incremental as it combines existing LLM and planning techniques.
The paper tackles the challenge of creating intelligent agents with human-like behavior in simulations by proposing a novel architecture that integrates a Large Language Model for decision-making with a classical automated planner for sound plan generation, resulting in agents capable of handling unanticipated situations.
In domains requiring intelligent agents to emulate plausible human-like behaviour, such as formative simulations, traditional techniques like behaviour trees encounter significant challenges. Large Language Models (LLMs), despite not always yielding optimal solutions, usually offer plausible and human-like responses to a given problem. In this paper, we exploit this capability and propose a novel architecture that integrates an LLM for decision-making with a classical automated planner that can generate sound plans for that decision. The combination aims to equip an agent with the ability to make decisions in various situations, even if they were not anticipated during the design phase.