Knowledgeable Automated Organization Design for Multi-Agent Systems

The ability to create effective multi-agent organizations is key to the development of larger, more diverse multi-agent systems. In this article we present KBORG: a fully automated, knowledge-based organization designer for multi-agent systems. Organization design is the process that accepts organizational goals, environmental expectations, performance requirements, role characterizations, and agent descriptions and assigns responsibilities and roles to each agent. These longterm responsibilities and roles serve as organizational-control guidelines that are used by each agent in making minute-by-minute operational control decisions. An important aspect of KB-ORG is its efficient, knowledge-informed search process for designing multi-agent organizations. KB-ORG uses both applicationlevel and coordination-level organization design knowledge to explore the combinatorial search space of candidate organizations selectively. KB-ORG also delays making coordination-level organizational decisions until it has explored and elaborated candidate application-level agent roles and responsibilities. This approach significantly reduces the exploration effort required to produce effective designs as compared to modeling and evaluation-based approaches that do not incorporate design expertise. In this article, we use examples from the distributed sensor network (DSN) domain to show how KB-ORG uses situational parameters as well as applicationlevel and coordination-level knowledge to generate organization designs. We also show that KB-ORG designs effective, yet substantially different, organizations when given different organizational requirements and environmental expectations.