Extending virtual organizations to improve trust mechanisms

Virtual Organizations (VOs) are becoming an increasingly important research topic in the field of Multi-Agent Systems (MAS). The problem of selecting suitable counterparts to interact with is of particular relevance for agents belonging to a VO. This issue has been extensively investigated, applying probability or cognitive approaches, but very few focus has been given to the use of internal organizational structures and the improvement they can provide. In this paper we analyze how organizational structures can support the agent selection process based an trust mechanisms. Furthermore, we present a way to extend VOs automatically (e.g., their role taxonomies) by detecting and identifying new roles. We show that such extensions lead to an improvement of the agents' decisions when employing trust mechanisms that take advantage of organizational structures.