Agent communication

Jacques Ferber has this to say when defining an agent . . .

An agent is a physical or virtual entity. . .

1. which is capable of acting in an environment.
   
2. which can communicate directly with other agents.
   
3. which is driven by a set of tendencies (in the form of individual objectives or of a satisfaction/survival function which it tries to optimize).
   
4. which possesses resources of its own.
   
5. which is capable of perceiving its environment (but to a limited extent).
   
6. which has only a partial representation of its environment (and perhaps none at all).
   
7. which possesses skills and can offer services.
   
8. which may be able to reproduce itself.
   
9. whose behaviour tends towards satisfying its objectives, taking account of the resources and skills available to it and depending on its perception, its representation and the communications it receives.
   

The part that gets me interested, of course, is item number 2 - the ability to communicate with other agents. Does this infer only agents that communicate using the same system? Or should there be, in an environment supporting the agile combination of agents from a variety of sources, the means for semantic communication between agents using a general system?

I'm betting that somewhere down the road, someone will be interested in the latter. I sure hope so.


Tags: agents, semantics, interoperability