Abstract
We present a Multi-Agent System (MAS) communication protocol for an Intelligent Learning Management System that provides, among others, collaborative services. The motivation behind this study stems from the need to enhance the possibilities of the current software architecture of the EUME project. Our aim is to improve intelligent resource management and communication efficiency. Our approach consists of applying the FIPA agent paradigm to the entire architecture, thus coming up with a fully multi-agent system. To show how the new system works, we also provide a study of communications in a number of typical collaborative scenarios.