CAPTURING AND MODELING COORDINATION KNOWLEDGE FOR MULTIAGENT SYSTEMS

The agent view provides a level of abstraction at which we envisage co mputational systems carrying out cooperative work by interoperating gl obally across networks connecting people, organizations and machines. A major challenge in building such systems is coordinating the behavio r of the individual agents to achieve the individual and shared goals of the participants. As part of a larger project targeted at developin g an Agent Building Shell for multiagent applications, we have designe d and implemented a coordination language aimed at explicitly represen ting, applying and capturing coordination knowledge for multiagent sys tems. The language provides KQML-based communication, an agent definit ion and execution environment, support for modeling interactions as mu ltiple structured conversations among agents, rule-based approaches to conversation selection and execution, as well as an interactive tool for in context acquisition and debugging of cooperation knowledge. The paper presents these components in detail and then shows how the coor dination language is used in the Agent Building Shell to manage conten t-based information distribution scenarios among agents and the coordi nation aspects of conflict management processes that occur when agents encounter inconsistencies. The major application of the system is the construction and integration of multiagent supply chain systems for m anufacturing enterprises. This application is used throughout the pape r to illustrate the introduced concepts and language constructs.