Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yizhi Xu

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.

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

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.

Paper Structure

This paper contains 17 sections, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. The CASCADE Architecture
  4. Overview
  5. Layer 1: Macro State Director
  6. Layer 2: Coordination Hub
  7. Layer 3: Tag-Driven NPCs
  8. Summary
  9. Evaluation
  10. Experimental Setup
  11. Results: Macro Event Impact on NPC Behavior
  12. Behavior Diversity and Cost Comparison
  13. Scalability and Performance Evaluation
  14. Conclusion of Evaluation
  15. Discussion
  16. ...and 2 more sections

Figures (1)

  • Figure 1: CASCADE Architecture: A Macro State Director drives the simulation, filtered through a Coordination Hub, and executed by Tag-Driven NPCs via local utility functions.