A Proposal to Extend the Common Model of Cognition with Metacognition
This work addresses the enhancement of cognitive architectures for researchers in AI and cognitive science, but it is incremental as it builds on an established model without introducing a new paradigm.
The paper tackles the problem of integrating metacognition into the Common Model of Cognition by proposing a unified approach that involves reasoning over explicit representations of cognitive capabilities in working memory, with minimal extensions to the existing structure.
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.