Coupling purposes with status-functions in artificial institutions

Abstract

In multi-agent systems, the agents may have goals that depend on a social, shared interpretation about the facts occurring in the system. These are the so-called social goals. Artificial institutions provide such a social interpretation by assigning statuses to the concrete elements that compose the system. These statuses are supposed to enable the assignee element to perform functions that are not exclusively inherent to their design features. However, the enabled functions are not explicit in the existing models of artificial institutions. As a consequence, (i) agents may have difficulties to reasoning about how to achieve their own social goals with the help of artificial institutions and (ii) these institutions are not well instrumented to receive incoming agents, in the case of open systems. Considering those problems, this paper proposes a model to express the functions -or the purposes -associated with the status-functions helping the agents to reason about their social goals and the institution. We evaluate the model by using it in some scenarios, showing how the agents can use purposes to reason about the satisfaction of their social goals in institutional contexts and how the institution can be flexible enough to support new agents operating in the system.