"To achieve flexible service provision software services can be endowed with self-* capabilities, such as self-adaptation and self-organisation, and service composition and management can take place autonomically. Such services are termed “polymorphic” since their functionality and structure vary dynamically. The view in the proposed project is that the autonomic behaviour of polymorphic services can be effectively supported by an agent architecture realising bio-inspired self-organisation and decentralised control models that are driven by user and business value criteria.The proposed research aims to contribute towards a framework for autonomic adaptation and composition of polymorphic services. The main objectives are:- Investigation of modelling principles and notations for representing polymorphic service adaptation and composition.- Development of an agent-based reference architecture implementing mechanisms for polymorphic service composition and management based on bio-inspired self-organisation and decentralised control models driven by user and business value criteria.- Integration of the above architecture in a cloud-based large-scale experimentation infrastructure and tuning of key framework parameters through experimentation.- Evaluation of the proposed approach (how well the polymorphic services approach satisfies the requirements of specific case studies) both quantitatively using simulations and qualitatively using opinions gathered with semi-structured interviews.The problem to be examined falls within the scope of the wider autonomic service composition problem currently tackled in large EU projects and the proposed approach significantly extends existing work in autonomic service composition and management by considering user and business value criteria, instead of only system infrastructure and performance ones, to drive autonomic service behaviours in polymorphic service composition and management."