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

arXiv: https://arxiv.org/abs/2512.18564 · HTML: https://mlsanity.com/paper/2512.18564/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 64 references that are in the map.
- First posted on arXiv 21 Dec 2025.

## Builds on (most cited first, 14 of 14)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [Explainable Reinforcement Learning: A Survey](https://mlsanity.com/paper/2005.06247/) (2020)
- [GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations](https://mlsanity.com/paper/2402.12348/) (2024)
- [A Survey on Large Language Model-Based Game Agents](https://mlsanity.com/paper/2404.02039/) (2024)
- [GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents](https://mlsanity.com/paper/2406.06613/) (2024)
- [AMONGAGENTS: Evaluating Large Language Models in the Interactive Text-Based Social Deduction Game](https://mlsanity.com/paper/2407.16521/) (2024)
- [Large Language Models and Video Games: A Preliminary Scoping Review](https://mlsanity.com/paper/2403.02613/) (2024)
- [Word2World: Generating Stories and Worlds through Large Language Models](https://mlsanity.com/paper/2405.06686/) (2024)
- [LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess](https://mlsanity.com/paper/2512.01992/) (2025)
- [TextQuests: How Good are LLMs at Text-Based Video Games?](https://mlsanity.com/paper/2507.23701/) (2025)
- [Digital Player: Evaluating Large Language Models based Human-like Agent in Games](https://mlsanity.com/paper/2502.20807/) (2025)

## Built on by (most cited first, 4 of 4)

- [CivBench: Progress-Based Evaluation for LLMs' Strategic Decision-Making in Civilization V](https://mlsanity.com/paper/2604.07733/) (2026)
- [To Nuke or Not to Nuke: LLMs' (Missing) Ethical Reasoning and Actions in a High-Stakes Decision-Making Simulation](https://mlsanity.com/paper/2606.08310/) (2026)
- [CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI](https://mlsanity.com/paper/2609.02459/) (2026)
- [Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization](https://mlsanity.com/paper/2609.18996/) (2026)

## Abstract (arXiv)

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.