The purpose of this paper is to discuss a framework for developing Intelligent Tutoring System (ITS) using multi-strata modeling scheme. The need far effective tutoring and training is mounting, especially in industry and engineering fields, which demand the teaming of complex tasks and knowledge, ITSs are being employed for this purpose, thus creating a need for cost-effective means of developing tutoring systems. In this study, learning processes are assumed as modeling of intelligent problem solving. There are various types of problem solving depending on its object and often more than one subjects concern the same problem solving with the different roles in a complex problem solving, In order to achieve the goal, new architecture of the system and new modeling scheme for representing problems including human activity are discussed as well as way of generating specific problem solving systems. Several new concepts are included in this study: a multi-level function structure and its corresponding knowledge structure, multiple meta-level operations, a multi-strata model to represent problems including human activity, large knowledge base, etc, in this paper, authors discuss a new approach to developing ITS that can generate tutoring systems for a wide range of domains.
