Marcin Paprzycki,

Computer Science Department, Oklahoma State University

Abstract:

For many years a message is being perpetuated that software agent technologies will become the next revolution in computer science. This change is to occur not only in the ways we construct software [2] but it is also to have a much broader impact on the field of human-computer interaction [1,3]. Unfortunately, as it is easy to see, the revolution that is prophesized since 1994 by the agent-believers does not materialize (regardless of the rapidly increasing number of conferences, workshops, special sessions, publications, etc). It is not the case that when we turn the computer on in the morning, we contact “our agent” to receive a personalized newscast, our day-plan and, on the basis of that plan as well as the weather forecast and knowledge of our dressing-preferences, an advice what to wear (agent ideal servant). Similarly, when creating software for an e-shop we do not utilize pre-existing agent-modules (e.g. advertising agents, inventory managers etc.). To the contrary, it is rather difficult to point to a successful large-scale implementation of an agent system.

The aim of the presentation will be three-fold. First, a general introduction to software agents will be presented followed by the discussion of major points raised “for” and “against” software agent systems (including highly critical analysis presented in [4]). Second, it will be shown, that it should be actually possible to develop large scale agent systems as state-of-the-art agent platforms like JADE scale up to more than a thousand agents and a few hundred thousand messages. Finally, a positive research program will be stated and illustrated using negotiating agents with dynamically loadable “reasoning” modules.

References
[1] J. Hendler, Is There an Intelligent Agent in Your Future?, Nature, 11 March, 1999, http://www.nature.com/nature/webmatters/agents/agents.html
[2] N. R. Jennings, An agent-based approach for building complex software systems,” Communications of the ACM, 44 (4), 2001, 35-41
[3] P. Maes. “Agents that Reduce Work and Information Overload.” Communications of the ACM, 37(7), 1994, 31-40
[4] H. Nwana, D. Ndumu, A perspective on software agents research, The Knowledge Engineering Review, 14 (2), 1999, 1-18

 

Date: 2005-Feb-21     Time: 13:30:00     Room: 905 (Auditório Omega)


For more information: