Multi-Actor Generative Artificial Intelligence as a Game Engine

2025-07-10

AI Summary

Current multi-agent generative AI systems exhibit limited flexibility, poor modularity, and low iterative efficiency in applications such as social science modeling, interactive narrative generation, and AI evaluation. To address these challenges, this paper proposes a tabletop role-playing game (TTRPG)-inspired multi-agent simulation framework. Its core innovation is a configurable and composable Game Master (GM) agent serving as a high-level coordinator, coupled with an Entity-Component architecture that decouples behavioral logic, state data, and configuration definitions. This design enables dynamic environment generation, customizable interaction rules, and rapid scenario reconfiguration. Integrated into the open-source Concordia library, the framework demonstrates empirically improved modularity, cross-scenario reusability, and scalable extensibility. It provides a reusable methodology and practical paradigm for the engineering development of generative multi-agent systems.

Technology Category

• Multiagent Systems: Modeling other Agents
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

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.

Problem

• Flexible scenario framework for multi-actor generative AI applications
• Game Master-inspired architecture for dynamic narrative generation
• Separation of engineering and design for modular scalable systems

Innovation

• Game Master as configurable entity
• Entity-Component architectural pattern
• Separation of implementation and design