Customizing Distributed Search Among Agents with Heterogeneous Knowledge

Negotiated search a paradigm for cooperative search and con ict resolution among heterogeneous reusable expert agents has been implemented in a exible frame work TEAM We present negotiated search and discuss the use of customized negotiated search strategies that take advantage of speci c capabilities and relationships that exist in an agent set Strategies are dynamically selected based on the individual agents views of the problem solving situation and on communicated knowl edge about the characteristics of agents in the agent set We present experiments that show strategies can reduce the amount of search required to nd mutually acceptable solutions and can improve the quality of those solutions The use of customized negotiated search strategies has far reaching implications for the design of agents that are intended to be reusable and for the assembly of agents into application systems