Apprentissage issu de la communication pour des agents cognitifs

Cognitive Agent communication is a field of research in full development. We propose here a model, based on the STROBE model, which regards the Agents as Scheme interpreters. These Agents are able to interpret messages of a conversation in both a given environment and an interpreter dedicated to the current conversation. These interpreters can moreover evolve dynamically progressively with the conversations and thus they represent meta level Agent knowledge. We propose a learning-by-communicating device to that level. This short paper presents briefly our model and its interest for domains such as the Web, services generation, the Grid etc... MOTS-CLÉS : communication agent, apprentissage par communication, interprétation dynamique, reifying procedures, STROBE, langage de communication agent.