A challenge for our days is to provide new efficient CASE (Computer Aided Software Engineering) tools enabling MAS designers towards Model Driven Engineering (MDE) approaches. The goal of MDE is to improve the de-velopment process and the quality of the software produced. Our work focuses on two different aspects of MAS. The functional one, which is application de-pendent and close to the decision process of agents, and the operational one related to elementary capabilities of agents. For each point of view, we have de-fined specific meta-models. Our goal in this paper is to provide a mapping from the functional meta-model to the operational that constitutes a specific platform model. As we are interested in adaptive systems, we have to deal with adaptation both at the agent and the system level. We address this problem by respectively using the JavAct flexible architecture and the Adaptive MAS principles.

Many Multi-Agent Systems (MAS) methodologies incorporate a model-driven approach. Model Driven Engineering is based on three main ideas: models are the "first-class citizens", meta-models define modelling languages that are used to specify models and models are transformed during the development. However, model transformation is still a challenging issue in MAS. At first, MAS designers are not necessarily familiar with existing model transformation languages or tools. Secondly, existing tools for creating model transformations do not satisfy the necessities of agent-oriented software engineering, since they focused on coding with little support for developers. This paper proposes a tool for the creation of model transformations that is based on the generation of model transformations by-example. This tool overcomes the limitations of other similar tools in the sense that it can generate many-to-many transformation rules. The tool application is exemplified with two MAS methodologies, INGENIAS and ADELFE.

The complexity of engineers tasks leads us to provide means to bring the Adaptive Multi-Agent Systems (AMAS) design to a higher stage of automation and confidence thanks to Model Driven Development (MDD). This paper focuses on a practical example and illustrates the modifications that have been done to the ADELFE methodology. In the Design phase, we propose to use a Domain Specific Modeling Language (DSML) for the specification of cooperative agents. We also, add a Model Diven Implementation phase using model transformation, DSMLs and code generation. These phases carry out a model centric process to produce and partially generate the system code. We present the use of our MD process applied to a simple, but very illustrative example: the foraging ants simulation.

The aim of this paper is to highlight how SPEM (Software and System Process Engineering Meta-model) 2.0 OMG (Object Management Group) can participate to design adaptive methodology process. The idea follows the FIPA Methodology Technical Committee (TC) one which consists in expressing a methodology in several fragments. Then, designer has to combine the relevant fragments to compose his own methodology. In this paper, we have chosen SPEM 2.0 OMG to express the fragments. The latest SPEM version improves methodology content and process re-usability, by introducing new capabilities as a clear separation between structural and dynamic methodology concerns. Those improvements in the field of methodology specification, are studied to determine their interests in the scope of Agent-Oriented Software Engineering (AOSE) and particularly, their impact on "methodology fragments" definition. ADELFE and PASSI methodologies have been taken as example to illustrate the use of SPEM 2.0 in the scope of "fragment" definition. In this paper, only the first step of the general objective consisting in expressing the fragments, is done and presented.