Efficient Development of Intelligent Test Generation Agents with the Disciple Learning Agent Shell

Disciple is a shell for developing intelligent agents where an expert teaches the agent how to perform domain-specific tasks in a way that resembles the way the expert would teach an apprentice. This paper discusses the application of Disciple to the development of educational agents that generate test questions for students, together with hints, answers and explanations, and assist in the assessment of students’ understanding and use of higher-order thinking skills. This work illustrates an integration of machine learning and intelligent-tutoring systems, in the context of computer-based assessment involving multimedia documents.