View article

Recovery in agent systems is an important and complex problem. This paper describes an approach to improving the robustness of an agent system by augmenting its failure-handling capabilities. The approach is based on the concept of semantic compensation: “cleaning up” failed or canceled tasks can help agents behave more robustly and predictably at both an individual and system level. However, in complex and dynamic domains it is difficult to define useful specific compensations ahead of time. This paper presents an approach to defining semantic compensations abstractly, then implementing them in a situation-specific manner at time of failure. The paper describes a methodology for decoupling failure-handling from normative agent logic so that the semantic compensation knowledge can be applied in a predictable and consistent way– with respect to both individual agent reaction to failure, and …