Cognitive Architectures and the Construction of Intelligent Agents

Pat Langley

A central aim of artificial intelligence and cognitive science is the construction of intelligent agents, which we can define as software artifacts that exhibit intelligent behavior in complex domains over extended periods of time. Intelligent agents can display different levels of functionality, but the long-term goal is to meet or exceed the broad range of capabilities that are found in human behavior. We should note that developing intelligent agents for complex domains requires the integration of different types of knowledge and different capabilities. To many, this suggests the use of software engineering methods, which focus on specifying interfaces between distinct modules. In contrast, the paradigm of cognitive architectures provides a unified approach in which a common set of representations and mechanisms reduce the need for such careful crafting. Thus, it provides an important and viable alternative for the construction of large-scale intelligent systems.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.