"Theater of Mind" for LLMs: A Cognitive Architecture Based on Global Workspace Theory
This addresses the bottleneck of autonomous artificial intelligence engineering for researchers and developers working with multi-agent LLM systems.
The paper tackles the problem of cognitive stagnation in multi-agent LLM systems by proposing Global Workspace Agents (GWA), a cognitive architecture based on Global Workspace Theory that transitions coordination to an active, event-driven system with entropy-based intrinsic drive and dual-layer memory, resulting in a framework for sustained, self-directed LLM agency.
Modern Large Language Models (LLMs) operate fundamentally as Bounded-Input Bounded-Output (BIBO) systems. They remain in a passive state until explicitly prompted, computing localized responses without intrinsic temporal continuity. While effective for isolated tasks, this reactive paradigm presents a critical bottleneck for engineering autonomous artificial intelligence. Current multi-agent frameworks attempt to distribute cognitive load but frequently rely on static memory pools and passive message passing, which inevitably leads to cognitive stagnation and homogeneous deadlocks during extended execution. To address this structural limitation, we propose Global Workspace Agents (GWA), a cognitive architecture inspired by Global Workspace Theory. GWA transitions multi-agent coordination from a passive data structure to an active, event-driven discrete dynamical system. By coupling a central broadcast hub with a heterogeneous swarm of functionally constrained agents, the system maintains a continuous cognitive cycle. Furthermore, we introduce an entropy-based intrinsic drive mechanism that mathematically quantifies semantic diversity, dynamically regulating generation temperature to autonomously break reasoning deadlocks. Coupled with a dual-layer memory bifurcation strategy to ensure long-term cognitive continuity, GWA provides a robust, reproducible engineering framework for sustained, self-directed LLM agency.