GRID Services as Learning Agents : Steps Towards Induction of Communication Protocols

In this article, we outline some issues in agent interaction on the Web, which is the center point of supporting the needs of fully-realized learning GRID in the future. Of particular importance is conversation support, with its core element, communication protocols. We propose to construct communication protocols through concept learning of services generated on the Web. The proposed approach incorporates a machine learning model into a conversation environment for the induction of communication protocols. 1. Motivation and Scenarios Real World Scenario. We unfold an important domain. [Clancey, 2004] presented a scenario of research collaborators, scientist who engage in a joint project. The author studies the collaboration between scientist at Haughton Crater in the High Canadian Artic. We have Z working with C on Devon Island, these people bring additional research capabilities to an effort. Each may be specialized in using particular instrument, or doing a particular kind of analysis. In defining joint research, collaborators often negotiate goals-such as (i.e. who will do what, how capabilities and efforts will leverage off of one another). They enter into a (usually informal) contract, or may write a research proposal to define roles and responsibilities. During