"Intelligent Agents meet the Semantic Web in the Aether

The concept of an agent is ubiquitous in Computer Science. We employ it to talk about and to model a wide range of things from physical robots, to modules in client-server architectures, to human, to Internet-based information retrieval programs, to intelligent personal assistants. During the past decade a "software agents" paradigm has emerged which views agents as autonomous, cooperating processes which use rich agent communication languages to exchange information and knowledge and to coordinate their activities. This has been seen as a way to capitalize on the opportunities (and solve many of the problems) created by the revolution brought about by the Internet and Web.

The vision has not yet materialized. Was it an example of an AI dream or "irrational exuberance" of the dot com era. I'll argue that the vision is still a good one and will describe how two new components might re-invigorate it. The first is the semantic web -- "an extension of the current web in which information is given well-defined meaning, better enabling computers and people to work in cooperation." The second is emergence of pervasive computing environments with requirements that multiagent systems are well suited to address. The argument will be illustrated using examples of current research at UMBC.