Previous: Desiderata for Agent Communication Languages
Up: Desiderata for Agent Communication Languages
The computational environment which is emerging in such programs as
the National Information Infrastructure (NII) is characterized by
being highly distributed, heterogeneous, extremely dynamic, and
comprising a large number of autonomous nodes. An information system
operating in such an environment must handle several emerging
A community of intelligent agents can address the first two of the
problems mentioned above. When we describe
agents as intelligent, we refer to their ability to: communicate
with each other using an expressive communication language; work
together cooperatively to accomplish complex goals; act on their own
initiative; and use local information and knowledge to manage local
resources and handle requests from peer agents.
The predominant architecture on the Internet, the cli
model, is too restrictive. It is difficult for current Internet
information services to take the initiative in bringing new, critical
material to a user's attention. Some nodes will want to act as both
clients and servers, depending upon with whom they are interacting.
Several forms of heterogeneity need to be handled, e.g. different
platforms, different data formats, the capabilities of different
information services, and the different standards (CORBA, OLE, LINDA,
ISIS, ZIRCON, OpenDoc, etc.) used by those services.
Many software technologies such as event simulation, applied natural
language processing, knowledge--based reasoning, advanced information
retrieval, speech processing, etc. have matured to the point of being
ready to participate in and contribute to an NII environment.
However, there is a lack of tools and techniques for constructing
intelligent clients and servers or for building agent--based software