Human cognition involves processes and phenomena taking place at scales ranging across orders of magnitude in time and complexity that Allen Newell called the bands of cognition. In this talk, I present evidence that cognitive architectures provide a unifying framework for knowledge and reasoning across the bands of cognition. Going down to the neural band, integrating symbolic knowledge and neural-like mechanisms enables the development of neuro-symbolic architectures that combine the strengths of neural learning and generalization and symbolic representations and inference. Going up to the rational band, bounded rationality is enabled by reflecting the statistical regularities of the environment in knowledge representation and reasoning mechanisms. However, systematic deviations from rationality known as cognitive biases emerge from the interaction between knowledge and reasoning limitations of cognitive architectures. Further up into the social band, integrating large groups of interacting cognitive agents enables the emergence of social and organizational knowledge and reasoning.

References

Anderson, J. R., Bothell, D., Byrne, M. D., Douglass, S., Lebiere, C., & Qin, Y. (2004). An Integrated Theory of the Mind. Psychological Review, 111(4), 1036–1060.

Laird, J. E., Lebiere, C. & Rosenbloom, P. S. (2017). A Standard Model of the Mind: Toward a Common Computational Framework across Artificial Intelligence, Cognitive Science, Neuroscience, and Robotics. AI Magazine 38(4).

Gonzalez, C., Lerch, F. J., & Lebiere, C. (2003). Instance-based learning in dynamic decision making. Cognitive Science 27(4): 591-635.

Lebiere, C., Blaha, L. M., Fallon, C. K., & Jefferson, B. (2021). Adaptive Cognitive Mechanisms to Maintain Calibrated Trust and Reliance in Automation. Frontiers in Robotics and AI (8).

Lebiere, C., Pirolli, P., Johnson, M., Martin, M., & Morrison, D. (2025). Cognitive Models for Machine Theory of Mind. Topics in Cognitive Science, 17(2). 268-290.