Through the Looking Glass: A Reconstructive Architecture for Machine Access Consciousness

A cognitive architecture called MIRROR, designed based on theories of access consciousness, separates immediate response generation from asynchronous deliberative processing. It uses an Inner Monologue Manager to create parallel cognitive threads and a Cognitive Controller to synthesize them into a bounded first-person narrative that is reconstructed each turn, mirroring human episodic memory. This narrative functions as an episodic buffer, making information globally available for reasoning. When tested on multi-turn dialogue requiring retention of personal safety constraints amid social pressure, MIRROR-augmented models achieved a 21% average improvement over baselines, with performance gains concentrated in scenarios requiring integration of temporally distant information. The authors do not claim MIRROR is conscious but offer it as a testbed for theoretical predictions.

Study at a glance

Abstract

Theories of access consciousness predict specific architectural signatures: parallel specialized processing, synthesis into a unified representation, and global availability for reasoning and action. We present MIRROR, a cognitive architecture that implements these features in large language models and tests whether they produce the functional behaviors these theories predict. MIRROR separates immediate response generation from asynchronous deliberative processing through two components: an Inner Monologue Manager that generates parallel cognitive threads (tracking goals, reasoning, and memory simultaneously), and a Cognitive Controller that synthesizes these threads into a bounded first-person narrative. Critically, this narrative is not accumulated but reconstructed each turn—mirroring the reconstructive nature of human episodic memory, where the self-model is continuously rebuilt rather than retrieved. The resulting representation functions as an episodic buffer: a limited-capacity workspace where information from parallel processes becomes globally available for downstream reasoning. We evaluated MIRROR on multi-turn dialogue requiring retention of personal safety constraints amid competing social demands—a task requiring relevant context to remain accessible across conversational turns despite distraction. MIRROR-augmented models achieve 21% average improvement over baselines, with the key finding being not the magnitude but the pattern: performance gains concentrate in scenarios requiring integration of temporally distant information under social pressure, precisely where access consciousness theories predict global availability provides advantage. These results offer three contributions to machine consciousness research: (1) a concrete implementation of architectural features derived from consciousness theories, (2) empirical evidence that these features produce predicted functional signatures, and (3) an interpretable system where internal states can be inspected. Note: We do not claim MIRROR is conscious; we claim it provides a testbed where theoretical predictions can be tested and examined.