Proceedings 2nd Asia-Pacific Conference on Intelligent Agent Technology (IAT-2001)
Agent Consumer Reports: of the Agents, by the Agents and for the Agents
October 23, 2001
Service matching is critical in large, dynamic agent systems. While finding exact matches is desirable when an agent knows what it wants, it is not always possible. Moreover, selected agents (even exact matches) may not provide quality services. Some agents may be unwilling or unable to advertise their capabilities in sufficient detail; some might unknowingly advertise inaccurate information, while others might even purposefully provide misleading information. Our proposed solution is the “Consumer Reports” agent. The broker agent will not only collect information advertised by service provider agents, but also learn from consumer agents' experiences with those service providers. It might also hire agents to test certain service providers to see how well they can do what they claim they can do. Then, we will build agent consumer reports based on the information collected. The advanced-level agent consumer reports will also dynamically capture the probabilistic distribution of services and use it to assess the probability of a match. We plan to extend LARKS and use it as our agent capability description language.
InProceedings
World Scientific Publishing Company
DOI 10.1142/9789812811042_0012
Downloads: 1609 downloads