The RETSINA multiagent infrastructure consists of a system of reusable agent types that can be adapted to address a variety of different domain-specific problems. Each RETSINA agent draws upon a sophisticated reasoning architecture that consists of four reusable modules for communication, planning, scheduling and execution monitoring.

A collection of RETSINA agents forms an open society of reusable entities that self-organize and cooperate in response to task requirements. We are currently applying this agent infrastructure to a number of domains, including information retrieval, team decision making, and financial portfolio management.