"Theater of Mind" for LLMs: A Cognitive Architecture Based on Global Workspace Theory

TL;DR

This paper introduces Global Workspace Agents, a novel cognitive architecture inspired by Global Workspace Theory, enabling autonomous, continuous, and self-regulating operation of large language models.

Contribution

It proposes a dynamic, event-driven multi-agent framework with entropy-based regulation and memory strategies to overcome passive, reactive limitations of current LLMs.

Findings

GWA maintains continuous cognitive cycles in LLMs.

Entropy-based drive regulates semantic diversity and reasoning flow.

Dual-layer memory ensures long-term cognitive continuity.

Abstract

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.