Computational Metacognition
This work addresses the challenge of improving high-order reasoning in artificial systems, though it appears incremental as it builds on existing metareasoning and human metacognition concepts.
The paper tackles the problem of enhancing intelligent systems' performance by implementing computational metacognition, which monitors and manages cognitive activity, and demonstrates its value in problem-solving through an agent in the MIDCA architecture.
Computational metacognition represents a cognitive systems perspective on high-order reasoning in integrated artificial systems that seeks to leverage ideas from human metacognition and from metareasoning approaches in artificial intelligence. The key characteristic is to declaratively represent and then monitor traces of cognitive activity in an intelligent system in order to manage the performance of cognition itself. Improvements in cognition then lead to improvements in behavior and thus performance. We illustrate these concepts with an agent implementation in a cognitive architecture called MIDCA and show the value of metacognition in problem-solving. The results illustrate how computational metacognition improves performance by changing cognition through meta-level goal operations and learning.