🤖 AI Summary
This study aims to systematically integrate metacognitive capabilities into the generic Cognitive Model of Cognition (CMC) to enhance its representational fidelity to human higher-order cognition.
Method: For the first time, we achieve symbolic modeling and reasoning over cognitive states—without altering CMC’s core architecture—by explicitly representing cognitive abilities and processes within working memory; no new modules or learning algorithms are introduced.
Contribution/Results: We propose a minimal, operationally grounded paradigm for metacognitive integration; formally define metacognition as “explicit symbolic reasoning about cognitive states”; and rigorously formalize canonical metacognitive behaviors—including strategy selection, monitoring, and debugging. This work establishes a verifiable, scalable theoretical and modeling foundation for human-level cognitive architectures.
📝 Abstract
The Common Model of Cognition (CMC) provides an abstract characterization of the structure and processing required by a cognitive architecture for human-like minds. We propose a unified approach to integrating metacognition within the CMC. We propose that metacognition involves reasoning over explicit representations of an agent's cognitive capabilities and processes in working memory. Our proposal exploits the existing cognitive capabilities of the CMC, making minimal extensions in the structure and information available within working memory. We provide examples of metacognition within our proposal.