A COLLABORATIVE LEARNING-ENVIRONMENT BASED ON INTELLIGENT AGENTS

One of the current trends in the research on Al applied to computer as sisted learning is the area of Computer Supported Collaborative Learni ng (CSCL). A CSCL environment should include software elements that as sist the learners in the application of the domain knowledge and promo te opportunities of effective collaboration and learning. In this pape r we present a CSCL environment based on two kinds of intelligent agen ts, domain agents and mediator agents, modeled based on ideas from dis tributed artificial intelligence. The domain agents are able to assist the learners in the application of domain knowledge elements. In orde r to support the collaboration between learners each mediator agent co nstructs and maintains a learner model represented as a set of beliefs about the capabilities, commitments, intentions and learning opportun ities of its learner. Mediator agents cooperate by exchanging their be liefs about the capabilities of their learners and proposing the pract ice of those knowledge elements that promote assistance among learners , keeping the group heterogeneous and collaborative. Based on its lear ner model the mediator agent is able to support awareness in the envir onment and maintain the learning possibilities of its learner in a com munity of practice. This framework provides a collaborative environmen t for second language learning based on an implementation of the theor etical concepts of social learning (Vygotsky, L. S., 1978, Mind in Soc iety: the Development of Higher Psychological Processes. London: Harva rd University Press) and agent oriented programming (Shoham, Y., 1993, Agent-oriented programming. Artificial Intelligence, 60, 51-92). (C) 1998 Elsevier Science Ltd. All rights reserved.