Abstract
Algorithms to determine the itinerary of agents are fundamental in the context of distributed applications based on mobile agents with timing requirements. To establish an agent's itinerary it is necessary to consider the trade-offs between achieving high-quality results while meeting firm deadlines. In this paper we describe and evaluate two adaptive heuristics that make a decision about the behavior for an agent at the beginning of its mission. The decision-making about the behavior is based on a log of benefits collected by the mobile agent in past executions. An agent adapts itself at the departure. Once chosen the behavior for a particular mission, the agent keeps this behavior until the end of the mission.