The 2003 International Symposium on Collaborative Technologies and Systems (CTS’03)
January 19 - 23, 2003
The Craft of Building Social Agents in Collaborative Enterprises
One of the major challenges for software development in the next decade with increased mobility and distributed work centers is to create the engineering principles and practices for easy-to-use, large-scale, highly interconnected and online information agents and systems. Exploring multiagent systems is an essential part of this challenge. Future collaborative technologies will employ agents in man-machine and machine-machine interfaces. Agents will become cognitive assistants capable of discovering human preferences, personality, and emotions. With this, agents will gain human trust and their own autonomy while providing greater human control. Agents will also form social networks that will facilitate their greater ability to work together and to collaborate. We envision agents that will be socially adept. This contributes to robustness and adaptability of collaborative enterprises. Theories and models of agent interaction are needed as part of collaborative enterprises to provide foundations for constructing systems able to work with each other and with the people using them.
Specific Goals and Objectives:
We hope to foster a growth of interest in multi-agent systems as part of collaborative enterprises. We will draw attention to areas of research and development in cognitively sophisticated agents.
In this tutorial Dr. Hexmoor will begin with an overview of agent architectures and software engineering approaches to multiagent systems. He will then discuss social attitudes among agents such as values, norms, and obligations. He will conclude by highlighting open problems and recent trends in multiagent system research.
Required Background and Intended Audience:
With this tutorial, we intend to address (a) participants with interest in collaboration and multiagency, and (b) practitioners and managers who are interested in directing research in collaborative enterprises.
Method of Presentation:
Power Point using LCD projector. Tutorial notes will be made available.
Computer Science and Computer Engineering Department
University of Arkansas
Fayetteville, AR, USA
Dr. Hexmoor is an Assistant Professor in the Department of Computer Science and Computer Engineering at the University of Arkansas. He earned his M.S. degree from Georgia Tech and PhD in Computer Science from SUNY at Buffalo, in 1996. Dr. Hexmoor taught at the University of North Dakota before joining the University of Arkansas. He has published widely in Artificial Intelligence and Multiagent Systems. His research interests include multiagent systems, artificial intelligence, Cognitive science, and mobile robotics.