# Multi-Actor Generative Artificial Intelligence as a Game Engine

*Source* · `src-vezhnevets-2025-multi-actor-game-engine` · status: **n/a**

| field | value |
|---|---|
| kind | Preprint |
| authors | Alexander Sasha Vezhnevets, Jayd Matyas, Logan Cross, Davide Paglieri, Minsuk Chang, William A. Cunningham, Simon Osindero, William S. Isaac, Joel Z. Leibo |
| venue | arXiv |
| date | 2025-07-10 |
| url | https://arxiv.org/abs/2507.08892 |
| arxiv | 2507.08892 |
| accessed | 2026-10-24 |

## Notes

Entity-Component pattern for Concordia: the Game Master is a configurable entity built from components; separates engineers (components) from designers (scenarios). Classifies multi-actor uses as Simulationist, Dramatist, and Evaluationist.

## Backlinks (computed)

**cited by:** [Many-agent LLM societies](../technique/llm-agent-societies.md), [LLM game master and narrative director](../technique/llm-game-master.md)

## Citation

Alexander Sasha Vezhnevets, Jayd Matyas, Logan Cross, Davide Paglieri, Minsuk Chang, William A. Cunningham, Simon Osindero, William S. Isaac, Joel Z. Leibo (2025-07-10). *Multi-Actor Generative Artificial Intelligence as a Game Engine*. arXiv https://arxiv.org/abs/2507.08892

---
Provenance: created in run `2026-10-24-techniques-llm-agents`.