| title | Intelligent Agents on the Web and in the Aether |
| authors | Tim Finin |
| http://www2.sis.pitt.edu/about/events/knowledge/index.html | |
| abstract | The concept of an agent is a ubiquitous and powerful one 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 interface components, to Internet-based information retrieval programs, to intelligent personal assistants. During the past decade the notion of an "intelligent software agent" as autonomous, cooperating processes which use rich agent communication languages to exchange information and knowledge and to coordinate their activities has caught the imagination of both researchers and venture capitalists. The agents paradigm has been seen as a way to capitalize on the opportunities (and solve many of the problems) created by the Internet revolution and the exploding world of electronic commerce. However, the vision has, for the most part, not yet materialized. Some will argue that this is yet another example of AI hype and the general technical "irrational exuberance" of the last five years. I'll argue that the vision is still a good one and will describe how two new components might reinvigorate it. The first is the semantic we—"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 development of mobile and pervasive computing environments which provide requirements which multiagent systems are well suited to address. |
| keywords | |
| bibtex |
@Presentation{FininPitt01Presentation , |
| citation | |
| paper | |
| handout | |
| slides | http://umbc.edu/~finin/papers/pitt01/slides.pdf |