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.

翻译：游戏平衡是一项长期存在的挑战，需要反复进行游戏测试、依赖专家直觉并进行大量手动调整。我们提出了RuleSmith，这是首个通过利用多智能体大语言模型的推理能力实现自动化游戏平衡的框架。该框架耦合了游戏引擎、多智能体大语言模型自博弈，以及在多维规则空间上运行的贝叶斯优化。作为概念验证，我们在CivMini上实例化了RuleSmith——这是一个简化的文明风格游戏，包含异质阵营、经济系统、生产规则和战斗机制，所有这些都由可调参数控制。大语言模型智能体通过解读文本规则手册和游戏状态来生成行动，从而快速评估如胜率差异等平衡性指标。为了高效搜索参数空间，我们将贝叶斯优化与基于采集函数的自适应采样及离散投影相结合：有潜力的候选配置会获得更多评估对局以实现精确评估，而探索性候选配置则获得较少对局以实现高效探索。实验表明，RuleSmith能够收敛到高度平衡的配置，并提供可直接应用于下游游戏系统的可解释规则调整。我们的研究结果证明，大语言模型仿真可以作为自动化复杂多智能体环境设计与平衡的强大替代方案。