In this paper, we present a framework for resolving conflicts between personal and normative goals in normative agent systems. The conflicts occur in the decision making process of time-constrained tasks of those goals. The agents observe the environment and perform the tasks based on their obligation to an authority, their desires, and intentions. They select and execute the tasks from a set of pre-compiled tasks based on their beliefs of the reward and penalty associated with the selected tasks. To resolve the conflicts within the constraint of the tasks’ duration, we supplement the agents’ normative capacity with two essential functions: Sacrifice and Diligence. The Sacrifice function enables an agent to reason and discard any tasks that have lower priorities to make way for accomplishment of the normative goal. The Diligence function enables an agent to increase its effort in accomplishing the normative goal in time-constrained situations. We simulate these situations and present the results.

No abstract

In this paper, the authors demonstrate the use of software agents to extend the role of humans in a collaborative work process. The extended roles to agents provide a convenient means for humans to delegate mundane tasks to software agents. The framework employs the FIPA ACL communication protocol which implements communication between agents. An interface for each agent implements the communication between humans and agents. Such interface and the subsequent communication performed by agents and between agents contribute to the achievement of shared goals.

No abstract

No abstract