To achieve interoperability between systems belonging to distributed organizations, a mechanism to rule how they interact with each other, without loosing their autonomy and keeping communication as flexible as possible, is necessary. In Multi-Agent Systems, interaction protocols were invented for this purpose. Simple UML-like diagrams have been used, focusing mostly in the specification of the sequence in which messages can be exchanged and who they can be sent to. Relevant details have been left out, making these models easy to understand for the reader, but at the same time less flexible, reusable, machine readable and hard to use for automatic development where more insights on the semantics of the model are necessary. We propose a declarative and more expressive model which makes use of well known contributions of the area of Multi-Agents. Adding more details inevitably increases complexity and to deal with it, we propose a model-driven tool. The tool is composed two parts, one is a graphical editor, which visualizes the semantics and effects of the definitions made by the designer, in real time and using planing algorithms. The other is an automatic code generator that produces Jadex BDI agents. Models created using our tool are more expressive, reusable, modular and can be used in automated development.

The article presents perspectives of how future directions in the development of the Internet could look like and how agents could support this evolution. The article describes recent Internet trends, discusses some ideas how future developments of the Internet might look like, presents some basics of agent technologies and discusses how agent technologies can contribute to the further development of the Internet.

Interoperability involves solutions at different levels, from concrete data representation to coordination of actions. These solutions are even more difficult to handle when the systems being integrated expect to remain autonomous. This is frequently the case in business processes between different organizations. In order to work together several technical and organizational issues have to be solved. One of the most important aspects is coordination and efficient communication. Interaction protocols have been introduced as conversation contracts between participants in order to solve this. Interaction protocols are very difficult to develop and maintain. The present work provides a consolidating model that enables modularity for interaction protocols design and reuse of solutions by composing them to fit the different scenarios.

The production of steel normally constitutes the inception of many Supply Chains in different areas of industry. Therefore, steel manufacturing companies are strongly affected by bull whip effects and other unpredictable influences along their production chains. In the course of these integrated operations, making the right decision at a certain stage can be the difference between earning or losing a great benefit. Improving their operational efficiency is required to keep a competitive position on the market. Therefore, flexible planning and scheduling systems are needed to support these processes, which are based on considerable amounts of data, hardly processable manually anymore. MasDISPO_xt is an agent-based generic online planning and scheduling system for the observation on MES-level of the complete Supply Chain of Saarstahl AG, a globally respected steel manufacturer. This paper concentrates on the planning of the annealing furnaces as a representative example of the rough and detailed planning required in such an environment. The allocation of available capacities of annealing furnaces including alternatives to accepted orders is based on Simulated Trading to produce an evenly distributed rough planning regarding flexibility. As representative for the detailed planning, the solution for the batch-type annealing furnace is explained in detail.

The representation of an agent organisation using a concrete computational entity is a frequently missing feature in platforms for multiagent systems, and it is normally left as a result of the emergent behaviour of interacting agents. This is also the case for JADE, one of the most used multiagent system platforms. This paper proposes an extension to JADE that addresses this missing concept, without disrupting the compatibility with previously developed systems nor the availability of JADE's platform services.

Integration of agents and Web Services has been target of much interest and significant work in the last few years. In this paper an openly available implementation of a FIPA compliant Jade Message Transport System for Web Services is presented and evaluated. It provides a mechanism to integrate Jade agents transparently with Web Services, The proposed message representation is compliant with FIPA and modern Web Services standards and is part of FIPA's initiative to create specifications for Web Services integration. Agent implementations do not require to be changed to interact with Web Services or to provide services using this tool. It also can be used to implement complex conversations as choreographies of Web Services.

In the majority of cases, steel production constitutes the inception of the Supply Chains they are involved Just as in automotive clusters or aerospace. Steel manufactunng companies are affected strongest by bull whip effects or other unpredictable influences along the production chain to the customers. Therefore, flexible planning and realisation as well as fast reorganisation after interferences are indispensable requirements for a competitive position on the market. In thiS paper, MasDISPO, an agent-based decision support system for production and control inside the steel works of Saarstahl AG, a globally respected steel manufacturer, is presented. It is based on a distributed online planning and online scheduling algorithm to calculate solutions supporting production and control inside the melting shop. It monitors the execution of their chosen solutions and responds to unpredicted changes during production by dynamically adapting the schedules. This paper gives an overview of the system, the approach for solving the complex problem of steel production and control, the development process, the main experiences as well as lessons learned.

The steel production of the German company Saarstahl AG, a global respected steel manufacturer, represents a Supply Chain which comprehends several time-critical and highly interference susceptible processes. Therefore, flexibility, robustness and fast reorganisation are indispensable requirements on a system responsible for the planning of production inside this Supply Chain to ensure acceptable costs and retain their respected position on this market. In this paper we present an agent-based generic solution for the planning and observation of the complete production process inside the steelwork Völklingen of Saarstahl AG. The presented system calculates solutions for given daily target schedules - based on the concrete orders by the customers - by a combined distributed online planning and scheduling algorithm, and, additionally, performs the observation of its realisation. Moreover, the presented real-time multiagent system supports the reorganisation after operational faults in this high dynamic context by suggesting new solutions to the responsible conductor.