Beyond Playtesting: A Generative Multi-Agent Simulation System for Massively Multiplayer Online Games

TL;DR

This paper introduces a generative multi-agent simulation system for MMO games that uses fine-tuned Large Language Models and real gameplay data to accurately mimic player behavior, enabling cost-effective optimization.

Contribution

It presents a novel LLM-based simulation framework that improves fidelity and interpretability over traditional offline models for MMO game optimization.

Findings

High consistency with real player behavior

Plausible causal responses to interventions

Cost-efficient and reliable simulation system

Abstract

Optimizing numerical systems and mechanism design is crucial for enhancing player experience in Massively Multiplayer Online (MMO) games. Traditional optimization approaches rely on large-scale online experiments or parameter tuning over predefined statistical models, which are costly, time-consuming, and may disrupt player experience. Although simplified offline simulation systems are often adopted as alternatives, their limited fidelity prevents agents from accurately mimicking real player reasoning and reactions to interventions. To address these limitations, we propose a generative agent-based MMO simulation system empowered by Large Language Models (LLMs). By applying Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) on large-scale real player behavioral data, we adapt LLMs from general priors to game-specific domains, enabling realistic and interpretable player decision-making. In parallel, a data-driven environment model trained on real gameplay logs reconstructs dynamic in-game systems. Experiments demonstrate strong consistency with real-world player behaviors and plausible causal responses under interventions, providing a reliable, interpretable, and cost-efficient framework for data-driven numerical design optimization.