One of the common ways to achieve interoperability among the autonomous agents is to use a broker agent (or a facilitator). The idea is, on the one hand, individual agents can advertise their capabilities to the broker agent; on the other hand, an agent can also ask the broker agent which agent(s) has certain capabilities (ask for recommendation). Simple broker agents provide match-making services based on the capability information volunteered by individual agents and the (recommendation) request. The problem is, even with a very good agent capability description language and a powerful match-making mechanism (such as LARKS), if the actual capability information volunteered by each individual agent is not accurate, it won't be of much help. Given that the autonomous agents might be written by different people, at different time, and for different purpose, this is likely to occur. For example, two Toyota car dealers (A and B) might give the same advertisement "We sell all models of Toyota cars, lowest price guaranteed". The fact might be that at dealer A, you have fewer or no choice of colors on popular models as you can at the other dealer. The service quality is different.
展开▼
