Beyond Playtesting: A Generative Multi-agent Simulation System For Massively Multiplayer Online Games

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 dyna

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2025beyond

Related papers

• Empowering Economic Simulation For Massively Multiplayer Online Games Through Generative Agent-based Modeling (2025)0.00
• Neural MMO V1.3: A Massively Multiagent Game Environment For Training And Evaluating Neural Networks (2020)0.00
• End-to-end Optimization Of Llm-driven Multi-agent Search Systems Via Heterogeneous-group-based Reinforcement Learning (2025)0.00
• Policyevolve: Evolving Programmatic Policies By Llms For Multi-player Games Via Population-based Training (2025)0.00
• Massively Multiagent Minigames For Training Generalist Agents (2024)0.00
• Agent-pro: Learning To Evolve Via Policy-level Reflection And Optimization (2024)9.59
• Generative Evolutionary Meta-solver (GEMS): Scalable Surrogate-free Multi-agent Reinforcement Learning (2025)0.00
• Neural MMO 2.0: A Massively Multi-task Addition To Massively Multi-agent Learning (2023)0.00