Vox Deorum: A Hybrid LLM Architecture for 4X / Grand Strategy Game AI -- Lessons from Civilization V

TL;DR

This paper introduces Vox Deorum, a hybrid LLM architecture for 4X and grand strategy games like Civilization V, demonstrating competitive gameplay and diverse AI behaviors through extensive testing.

Contribution

It presents a layered hybrid architecture that enables LLMs to handle macro-strategic reasoning while delegating tactical tasks, advancing AI integration in complex strategy games.

Findings

LLMs achieve competitive gameplay performance.

Play styles of LLMs differ significantly from traditional AI.

The architecture is viable for commercial 4X game integration.

Abstract

Large Language Models' capacity to reason in natural language makes them uniquely promising for 4X and grand strategy games, enabling more natural human-AI gameplay interactions such as collaboration and negotiation. However, these games present unique challenges due to their complexity and long-horizon nature, while latency and cost factors may hinder LLMs' real-world deployment. Working on a classic 4X strategy game, Sid Meier's Civilization V with the Vox Populi mod, we introduce Vox Deorum, a hybrid LLM+X architecture. Our layered technical design empowers LLMs to handle macro-strategic reasoning, delegating tactical execution to subsystems (e.g., algorithmic AI or reinforcement learning AI in the future). We validate our approach through 2,327 complete games, comparing two open-source LLMs with a simple prompt against Vox Populi's enhanced AI. Results show that LLMs achieve competitive end-to-end gameplay while exhibiting play styles that diverge substantially from algorithmic AI and from each other. Our work establishes a viable architecture for integrating LLMs in commercial 4X games, opening new opportunities for game design and agentic AI research.