RuleSmith: Multi-Agent LLMs for Automated Game Balancing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917252540923904 |
|---|---|
| author | Zeng, Ziyao Liu, Chen Liu, Tianyu Wang, Hao Sun, Xiatao Yang, Fengyu Liu, Xiaofeng Fan, Zhiwen |
| author_facet | Zeng, Ziyao Liu, Chen Liu, Tianyu Wang, Hao Sun, Xiatao Yang, Fengyu Liu, Xiaofeng Fan, Zhiwen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06232 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RuleSmith: Multi-Agent LLMs for Automated Game Balancing Zeng, Ziyao Liu, Chen Liu, Tianyu Wang, Hao Sun, Xiatao Yang, Fengyu Liu, Xiaofeng Fan, Zhiwen Machine Learning Artificial Intelligence Computer Science and Game Theory Multiagent Systems 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. |
| title | RuleSmith: Multi-Agent LLMs for Automated Game Balancing |
| topic | Machine Learning Artificial Intelligence Computer Science and Game Theory Multiagent Systems |
| url | https://arxiv.org/abs/2602.06232 |