R. Michael Young, North Carolina State University
Intelligent agents are often called upon to form plans that direct their own or other agents’ activities. For these systems, the ability to describe plans to people in natural ways is an essential aspect of their interface. In this paper, we present the Cooperative Plan Identification (CPI) architecture, a computational model that generates concise, effective textual descriptions of plan data structures. The model incorporates previous theoretical work on the comprehension of plan descriptions, using a generate-and-test approach to perform efficient search through the space of candidate descriptions. We describe an empirical evaluation of the CPI architecture in which subjects following instructions produced by the CPI architecture performed their tasks with fewer execution errors and achieved a higher percentage of their tasks' goals than did subjects following instructions produced by alternative methods.