Giving Personal Assistant Agents a Case-Based Memory

We consider Personal Assistant (PA) agents as cognitive agents capable of helping users handle tasks at their workplace. A PA must communicate with the user using casual language, sub-contract the requested tasks, and present the results in a timely fashion. This leads to fairly complex cognitive agents. However, in addition, such an agent should learn from previous tasks or exchanges, which will increase its complexity. Learning requires a memory, which leads to the two following questions: Is it possible to design and build a generic model of memory? If it is, is it worth the trouble? The article tries to answer the questions by presenting the design and implementation of a memory for PA agents, using a case approach, which results in an improved agent model called MemoPA.