Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

Managing information flow for complex, dynamic tasks using multi-agent collaboration

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
5 Author(s)
Mukhopadhyay, S. ; Dept. of Comput. & Inf. Sci., Indiana Univ., Indianapolis, IN, USA ; Palakal, M. ; Kodiripaka, V. ; Raje, R.
more authors

In this paper, we present a multi-agent information system model that can deal with complex multi-activity information-driven tasks. After defining a single information agent architecture in an abstract way, we describe the multi-agent model (called the parallel model), as well as a simple collaboration protocol for the multiple activity information agents. Experimental results are presented with the multi-agent system that demonstrate that a significantly larger number of relevant documents can be retrieved through collaboration than what is possible with decoupled agents. Hence, such multi-agent parallel models appear to hold considerable promise in providing the user with high quality information services in a variety of business and scientific information-driven tasks.

Published in:

Intelligent Control. 2003 IEEE International Symposium on

Date of Conference:

8-8 Oct. 2003