CASCADE: A Cascading Architecture for Social Coordination with Controllable Emergence at Low Cost
This addresses the challenge for game developers of achieving rich social behavior in sandbox-style games at reduced runtime costs, though it is incremental as it builds on existing methods like behavior trees and LLMs.
The paper tackles the problem of balancing authorial control and computational cost in creating scalable game societies by introducing CASCADE, a three-layer architecture that enables low-cost, controllable social coordination, producing differentiated NPC behaviors without per-agent prompting in the main simulation loop.
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.