Using Systemions to Model Emergence in Learning Environments

Recent trends in multi-agent ITS can be split in a movement away from the traditional ITS architecture consisting of modules (i.e., the expert, student, and instructional modules) and a movement towards looking at the process (i.e., planning, monitoring, and diagnosing). The strong idea as a core assumption for this second approach is that the term "cognitive agent" can be described as an agent that learns in the same way as people learns. So, focus is put both on learning protocols and mutant processes within a new paradigm for cognitive agents: the Systemion (Systemic Daemon). Systemions are designed as agents that powerfully increase their knowledge by learning from other and agents that assume their survival by joining two unique properties of the living systems: replication and evolution. Life cycle in systemions is self-controlled by two concurrent mechanisms - first, a reproduction system, continuously modified by a learning algorithm, is used to fertilize the cloning of a "child" agent into a given lineage; - second, selective genetic algorithms act as a mutant processes to create new fathers of an improved lineage.