Developing web-based tutoring agents using CORBA

In this paper, we introduce an agent-based approach for the design and implementation of a Web-based learning environment in general chemistry pre-laboratory domain by taking advantage of the common object request broker architecture (CORBA). Four kinds of agents are investigated: the student modeler that models students' learning progress, the expert agents that simulate domain expertise, the intelligent tutoring tool (ITT) that scaffolds students' problem-solving processes and the adaptive lecture guidance (ALG) that presents students with adaptive navigating plan in Web-based environment. The advantages of this approach approach are two-fold. First, the CORBA middleware provides the distributed communication infrastructure for agents to cooperate and to produce intelligent tutoring behaviors. This in turn is important to achieve learning efficiency in WWW environment. Second, the modularity and platform independent character of these agents has great potential in supporting cost-effective reuse and cooperative development of educational content.