Published in Proceedings of the 6th International Conference on Tools with Artificial Intelligence: New Orleans, LA, November 6, 1994, pages 608-614. http://dx.doi.org/10.1109/TAI.1994.346385.
© 1994 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
Multi-agent systems provide an attractive architecture for the implementation of complex systems. Much of the research is focussed on complete automation of the decision making process as a means of duplicating human abilities for working with new problems and environments. There as also a need for systems that employ the human as an agent and rely on human abilities for common sense and deep thought. The CAD Research Center at Cal Poly and CDM Technologies have significant experience in building systems of the latter type that assist human users in solving complex problems in planning, design and economics. This experience has generated a set of guidelines and a software development framework that have collectively been identified as ICDM. This paper presents a brief history of major applications built with the ICDM framework, and proposes some basic precepts.