Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling
This work addresses the problem of improving agent reliability, sociability, and interpretability in economic simulations for MMO games, representing an incremental advancement by applying LLMs to a known bottleneck in agent-based modeling.
The study tackled the challenge of emulating human-like economic activities in Massively Multiplayer Online game simulations by introducing a novel approach using Large Language Models to design agents with role-playing, perception, memory, and reasoning abilities, resulting in emergent phenomena such as role specialization and price fluctuations that align with market rules.
Within the domain of Massively Multiplayer Online (MMO) economy research, Agent-Based Modeling (ABM) has emerged as a robust tool for analyzing game economics, evolving from rule-based agents to decision-making agents enhanced by reinforcement learning. Nevertheless, existing works encounter significant challenges when attempting to emulate human-like economic activities among agents, particularly regarding agent reliability, sociability, and interpretability. In this study, we take a preliminary step in introducing a novel approach using Large Language Models (LLMs) in MMO economy simulation. Leveraging LLMs' role-playing proficiency, generative capacity, and reasoning aptitude, we design LLM-driven agents with human-like decision-making and adaptability. These agents are equipped with the abilities of role-playing, perception, memory, and reasoning, addressing the aforementioned challenges effectively. Simulation experiments focusing on in-game economic activities demonstrate that LLM-empowered agents can promote emergent phenomena like role specialization and price fluctuations in line with market rules.