Multi-Actor Generative Artificial Intelligence as a Game Engine
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913938855165952 |
|---|---|
| author | Vezhnevets, Alexander Sasha Matyas, Jayd Cross, Logan Paglieri, Davide Chang, Minsuk Cunningham, William A. Osindero, Simon Isaac, William S. Leibo, Joel Z. |
| author_facet | Vezhnevets, Alexander Sasha Matyas, Jayd Cross, Logan Paglieri, Davide Chang, Minsuk Cunningham, William A. Osindero, Simon Isaac, William S. Leibo, Joel Z. |
| contents | Generative AI can be used in multi-actor environments with purposes ranging from social science modeling to interactive narrative and AI evaluation. Supporting this diversity of use cases -- which we classify as Simulationist, Dramatist, and Evaluationist -- demands a flexible scenario definition framework. We argue here that a good approach is to take inspiration from tabletop role-playing games (TTRPGs), where a Game Master (GM) is responsible for the environment and generates all parts of the story not directly determined by the voluntary actions of player characters. We argue that the Entity-Component architectural pattern is useful here. In such a system, the GM is not a hardcoded computer game but is itself a configurable entity, composed of components just like any other actor. By design, the approach allows for a separation between the underlying implementation details handled by an engineer, the creation of reusable components, and their composition and configuration managed by a designer who constructs entities from the components. This separation of concerns is instrumental for achieving rapid iteration, maintaining modularity, and ultimately to ensure scalability. We describe the ongoing evolution of the Concordia library in terms of this philosophy, demonstrating how it allows users to effectively configure scenarios that align with their specific goals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_08892 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Actor Generative Artificial Intelligence as a Game Engine Vezhnevets, Alexander Sasha Matyas, Jayd Cross, Logan Paglieri, Davide Chang, Minsuk Cunningham, William A. Osindero, Simon Isaac, William S. Leibo, Joel Z. Artificial Intelligence Multiagent Systems Generative AI can be used in multi-actor environments with purposes ranging from social science modeling to interactive narrative and AI evaluation. Supporting this diversity of use cases -- which we classify as Simulationist, Dramatist, and Evaluationist -- demands a flexible scenario definition framework. We argue here that a good approach is to take inspiration from tabletop role-playing games (TTRPGs), where a Game Master (GM) is responsible for the environment and generates all parts of the story not directly determined by the voluntary actions of player characters. We argue that the Entity-Component architectural pattern is useful here. In such a system, the GM is not a hardcoded computer game but is itself a configurable entity, composed of components just like any other actor. By design, the approach allows for a separation between the underlying implementation details handled by an engineer, the creation of reusable components, and their composition and configuration managed by a designer who constructs entities from the components. This separation of concerns is instrumental for achieving rapid iteration, maintaining modularity, and ultimately to ensure scalability. We describe the ongoing evolution of the Concordia library in terms of this philosophy, demonstrating how it allows users to effectively configure scenarios that align with their specific goals. |
| title | Multi-Actor Generative Artificial Intelligence as a Game Engine |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2507.08892 |