Training compositional agents in negotiation protocols using ontologies

The Internet facilitates the creation of new markets, which has motivated the development of new technologies for e-commerce. The increasing number of e-markets poses a big challenge to designers of e-commerce services. Agent-based applications are the most appropriate for merchandising because software agents are suitable for automating tedious tasks that the user may have to perform, such as, searching for goods. Furthermore, software agents are able to negotiate on the user’s behalf according to negotiation protocols. However, new challenges arise from the evolution of negotiation mechanisms. The lack of protocol interoperability at the application level is preventing the evolution of negotiation since the set of interaction protocols supported by a software agent is usually fixed once the agent is created, and any protocol adaptation needs agent replacement. Thus, new software technologies for the development of more flexible, adaptable and reusable software agents are needed. We propose the use of component technology for the development of adaptive software agents for new negotiations protocols. In this paper we describe the compositional architecture of a software agent, and how we take advantage of component orientation for training agents in new negotiation mechanisms at runtime.