AAAI Workshop on Cooperation Among Heterogeneous Intelligent Agents

Each session consisted of two papers, each of which was allotted 25 minutes for presentation, and a 25-minute discussion that was led by a member of the organizing committee. This format was adopted because the organizers believed that the single day that was allocated to the workshop was conducive to in-depth presentation of a small number of papers that would lead to issue-oriented discussions. The sections in this article bring forward points that were made during the workshop's four sessions. Recent attempts to develop larger and more complex knowledge-based systems have revealed the shortcomings and problems of centralized, single-agent architectures and have acted as a springboard for research in distributed AI (DAI). Although initial research efforts in DAI concentrated on issues relating to homogeneous systems (that is, systems using agents of a similar type or with similar knowledge), there is now increasing interest in systems comprised of heterogeneous components.