CASCADE: A Cascading Architecture for Social Coordination with Controllable Emergence at Low Cost

TL;DR

CASCADE introduces a three-layer architecture enabling scalable, controllable social coordination in game worlds by combining macro-level management, domain-specific modules, and on-demand LLM-driven NPC responses.

Contribution

The paper presents CASCADE, a novel modular architecture that balances authorial control and computational efficiency for social simulation in games.

Findings

Shared macro events produce differentiated NPC behaviors.

CASCADE reduces LLM usage by localizing it to player-facing interactions.

The architecture supports scalable and believable social simulation.

Abstract

Creating scalable and believable game societies requires balancing authorial control with computational cost. Existing scripted NPC systems scale efficiently but are often rigid, whereas fully LLM-driven agents can produce richer social behavior at a much higher runtime cost. We present CASCADE, a three-layer architecture for low-cost, controllable social coordination in sandbox-style game worlds. A Macro State Director (Level 1) maintains discrete-time world-state variables and macro-level causal updates, while a modular Coordination Hub decomposes state changes through domain-specific components (e.g., professional and social coordination) and routes the resulting directives to tag-defined groups. Then Tag-Driven NPCs (Level 3) execute responses through behavior trees and local state/utility functions, invoking large language models only for on-demand player-facing interactions. We evaluate CASCADE through multiple micro-scenario prototypes and trace-based analysis, showing how a shared macro event can produce differentiated yet logically constrained NPC behaviors without per-agent prompting in the main simulation loop. CASCADE provides a modular foundation for scalable social simulation and future open-world authoring tools.