RuleSmith: Multi-Agent LLMs for Automated Game Balancing

2026-02-05

AI Summary

This work proposes the first fully automated game balance optimization framework based on multi-agent large language models (LLMs), addressing the reliance on manual trial-and-error and expert intuition in traditional balancing practices. The approach integrates a game engine, LLM-driven self-play simulation, and Bayesian optimization to efficiently explore high-dimensional rule spaces. LLMs interpret rule texts and game states to generate strategic actions, while an adaptive acquisition function combined with discrete projection techniques enhances sampling efficiency. Experiments on the CivMini game demonstrate that the framework rapidly converges to highly balanced parameter configurations, substantially improving tuning efficiency and producing interpretable, directly deployable rule modifications.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Multiagent Systems: Mechanism Design
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Game balancing is a longstanding challenge requiring repeated playtesting, expert intuition, and extensive manual tuning. We introduce RuleSmith, the first framework that achieves automated game balancing by leveraging the reasoning capabilities of multi-agent LLMs. It couples a game engine, multi-agent LLMs self-play, and Bayesian optimization operating over a multi-dimensional rule space. As a proof of concept, we instantiate RuleSmith on CivMini, a simplified civilization-style game containing heterogeneous factions, economy systems, production rules, and combat mechanics, all governed by tunable parameters. LLM agents interpret textual rulebooks and game states to generate actions, to conduct fast evaluation of balance metrics such as win-rate disparities. To search the parameter landscape efficiently, we integrate Bayesian optimization with acquisition-based adaptive sampling and discrete projection: promising candidates receive more evaluation games for accurate assessment, while exploratory candidates receive fewer games for efficient exploration. Experiments show that RuleSmith converges to highly balanced configurations and provides interpretable rule adjustments that can be directly applied to downstream game systems. Our results illustrate that LLM simulation can serve as a powerful surrogate for automating design and balancing in complex multi-agent environments.

Problem

• game balancing
• automated tuning
• multi-agent systems
• rule adjustment
• balance metrics

Innovation

• multi-agent LLMs
• automated game balancing
• Bayesian optimization
• adaptive sampling
• rule interpretation