In-Context Information Management through Adaptive Collaboration of Intelligent Agents

Summary

Although the number and availability of electronic information sources are increasing, current information technology requires manual manipulation and user-specification of all details. Once accessed, information must be filtered in the context of the user’s task. Current systems lack the ability to get contextual information or use it to automate filtering. At Carnegie Mellon University, we have been engaged in the RETSINA project, which aims to develop a reusable multiagent software infrastructure that allows heterogeneous agents on the Internet, possibly developed by different designers, to collaborate with each other to manage information in the context of user-specified tasks. In this chapter, we will provide a brief overview of the whole system and then focus on its capability for in-context information management.

This research has been supported in part by DARPA contract F30602-98-2-0138, and by ONR Grant N00014-96-1222.