MIRROR: Converging Cognitive Principles as Computational Mechanisms for AI Reasoning

TL;DR

This paper introduces MIRROR, an AI architecture inspired by cognitive theories, demonstrating that converging human cognitive principles can improve multi-turn dialogue performance across diverse models.

Contribution

MIRROR operationalizes multiple cognitive principles into a unified AI system, showing computational advantages in dialogue tasks and validating theories through ablation studies.

Findings

21% relative improvement in dialogue performance

Reconstructive synthesis enhances all models (+5-20%)

Integrated system outperforms individual components in most models

Abstract

Multiple cognitive theories -- Global Workspace Theory, reconstructive episodic memory, inner speech, and complementary learning systems -- converge on a shared set of architectural principles: parallel specialized processing, integrative synthesis into a bounded unified representation, and reconstructive rather than accumulative maintenance. We test whether these converging principles provide computational advantages when implemented in AI systems. MIRROR operationalizes each principle as a concrete mechanism: an Inner Monologue Manager generates parallel cognitive threads (Goals, Reasoning, Memory), a Cognitive Controller synthesizes these into a bounded first-person narrative that is fully reconstructed each turn, and a temporal separation between fast response generation and slow deliberative consolidation mirrors complementary learning dynamics. Evaluated on multi-turn dialogue requiring constraint maintenance under attentional interference, MIRROR yields 21% relative improvement across seven architecturally diverse language models. Ablation studies test the theoretical predictions directly: reconstructive synthesis improves all seven models (+5-20%); the integrated system outperforms either component alone for six of seven models, confirming that parallel exploration and integrative synthesis are complementary; and gains concentrate where theories predict -- under high attentional load where global availability of integrated information is most needed. These results demonstrate that converging principles from human cognition provide architecture-general computational advantages, and generate testable behavioral predictions about working memory, inner speech, and memory consolidation. Project page available at https://www.arcarae.com/research/MIRROR and code at https://github.com/arcarae/MIRROR.