This is the eighth year that the Agent-Oriented Information Systems (AOIS) workshops have been held. Papers submitted to AOIS show an increase in quality and maturity as agent technology is being increasingly seen as a viable alternative for software and systems development. In AOIS, we focus on the application of agent technology in information systems development and explore the potential for facilitating the increased usage of agent technology in the creation of information systems in the widest sense. This year's workshops were held in conjunction with two major, international computing research conferences: the first, in May 2006, was affiliated with the AAMAS conference in Hakadote, Japan and chaired by Garcia, Ghose and Kolp. The second was held in conjunction with the international CAiSE conference held in Luxembourg (June 2006) and chaired by Bresciani, Henderson-Sellers and Mouratidis. (Details of all preceding workshops are to be found at http:// www. aois. org. ) The best papers from both these meetings were identified and authors invited to revise and extend their papers in light of the reviewers' comments and feedback at the workshop. Following submission to this compendium volume, another round of reviews was undertaken resulting in what you can read here. These re-reviews were undertaken by three members of the Programme Committee - we wish to thank both the authors for undertaking the necessary revisions and the reviewers for this extra call on their precious time.

The papers selected for this volume present advances in software engineering approaches to develop dependable high-quality multi-agent systems. These papers describe experiences and techniques associated with large multi-agent systems in a wide variety of problem domains. They cover fault tolerance, exception handling and diagnosis, security and trust, verification and validation, as well as early development phases and software reuse.

This book presents a coherent, well-balanced survey of recent advances in software engineering approaches to the design and analysis of realistic large-scale multi-agent systems (MAS). The chapters included are devoted to various techniques and methods used to cope with the complexity of real-world MAS. Reflecting the importance of agent properties in today's software systems, the power of agent-based software engineering is illustrated using examples that are representative of successful applications.

This book presents a coherent and well-balanced survey of recent advances in software engineering approaches to the design and analysis of realistic large-scale multi-agent systems (MAS). The chapters included are devoted to various techniques and methods used to cope with the complexity of real-world MAS. The power of agent-based software engineering is illustrated using examples that are representative of successful applications.

The 16 thoroughly reviewed and revised full papers are organized in topical sections on agent methodologies and processes, requirements engineering and software architectures, modeling languages, and dependability and coordination. Most of the papers were initially presented at the 3rd International Workshop on Software Engineering for Large-Scale Multi-agent Systems, SELMAS 2004, held in Edinburgh, UK in May 2004 in association with ICSE 2004. Other papers were invited to complete coverage of all relevant aspects.

Advances in networking technology have revitalized the investigation of agent technologyasapromisingparadigmforengineeringcomplexdistributedsoftware systems. Agent technology has been applied to a wide range of application - mains, including e-commerce, human-computer interfaces, telecommunications, and software assistants. Multi-agent systems (MASs) and their underlying t- ories provide a more natural support for ensuring important properties such as autonomy, mobility, environment heterogeneity, organization, openness, and intelligence. As a consequence, agent-based systems are likely to provide new - proaches to dealing with the complexity of developing and maintaining modern software. However, developing robust large-scale agent-based systems will - quire new software engineering approaches. There are currently many methods and techniques for working with individual agents or with systems built using only a few agents. Unfortunately, agent-based software engineering is still in its infancy and existing software engineering approaches are unable to cope with large MASs. The complexity associated with a large MAS is considerable. When a huge number of agents interact over heterogeneous environments, various phenomena occur which are not as easy to capture as when only a few agents are working together. As the multiple software agents are highly collaborative and operate in networked environments, they have to be context-aware and deal with - vironment uncertainty. This makes their coordination and management more di?cult and increases the likelihood of exceptional situations, such as security holes, privacy violations, and unexpected global e?ects. Moreover, as users and softwareengineersdelegatemoreautonomytotheirMASs, andputmoretrustin their results, new concerns arise in real-life applications

Nowadays, engineering large-scale software systems means dealing with complex systems composed of pervasive software components that move around and adapt to nondeterministic and open environments, like the Internet, in order to achieve systems design goals through the coordination of autonomously distributed services. The agent metaphor, in particular software agents and multi-agent systems (MAS), constitutes a promising approach for covering most of the software development life cycle, from conceptual modeling and requirements specification to architectural definition, design, and implementation. This book presents 17 carefully reviewed papers arranged in order to provide a coherent survey of how to exploit agent properties and MAS issues in today's software systems. The book offers the following topical sections: - software engineering foundations - requirements engineering and software architecture - coordination and mobility - reuse -dependability -empirical studies and applications