HongAvg: Hierarchical On-Demand Cognitive Split Federated Learning for Twin Agent Orchestration

Abstract

Fusing digital twins (DTs) with world models (WMs) promises a leap from reactive monitoring to proactive control. However, deploying high-fidelity WMs faces a fundamental cognitive gap: the immense computational demand of foundation models conflicts with the resource constraints of 6G edge nodes, while privacy regulations hinder the centralization of raw sensory data required for training. To bridge this gap, this paper presents HongAvg, a hierarchical on-demand cognitive split federated learning framework designed as cognitive infrastructure for next-generation DTs. By establishing a national-basin-edge three-tier architecture, HongAvg introduces foundation models to resource-constrained edges via split computing, offloading heavy cognitive reasoning while preserving data privacy. We propose a dual-stream semantic consistency mechanism to align edge interactions with the foundation model's cognition, ensuring that distributed cognitive primitives serve as valid inputs for global state estimation. Validated on a heterogeneous benchmark, HongAvg serves as a prototype for industrial cognitive computing, improving accuracy in visual monitoring by up to 8.9% and reducing edge memory usage by approximately 75%. This work provides the scalable architectural prerequisite necessary for evolving static DTs into proactive WM-driven multi-agent orchestrated intelligent systems.