This dissertation explores the feasibility of employing software agent technology to support large-scale assessment. The research included the design, development, and evaluation of the Assessment Agent System for assessing comprehensive understanding based on concept maps.

The system was designed by following an agent-oriented software design method. The Assessment Agent System is composed of five types of software agents: instructor agent, student agent, management agent, assessment agent, and reporting agent. Each of these agents was designed to possess different capabilities. Software agents in the system, through communication and cooperation, collectively provide the functionalities of user-system interaction, user management, task authoring and management, assessment delivery, task presentation, response collection, automatic assessing with feedback, and reporting. Through the process of design, development, and evaluation of the Assessment Agent System, this study demonstrates an approach that employs an agent-oriented software design method to produce sophisticated educational software applications.

Furthermore, this study explored the concept map assessing method for the Assessment Agent System. When node terms and linking phrases are provided, assessing student concept maps can be automated by comparing student concept maps with assessment criteria, proposition by proposition. However, the usefulness of the proposition-comparing method depends heavily on the accuracy and thoroughness of the criterion propositions. Therefore, assessment criteria need to be continually refined and improved through examining student-created propositions.