Introduction

Intelligent agent technology, of which the holonic approach is a subset, is at an interesting point in its development. Commercial strength agent applications are increasingly being developed in domains as diverse as meteorology (Mathieson et al, 2004), manufacturing (Bussmann et al, 2004), war gaming (Heinze et al, 2002; Lui et al, 2002), and UAV flight management (Karim and Heinze, 2005; Jarvis, J. et al, 2006a, 2006b). Furthermore, industrial strength development environments are available, such as Soar (University of Michigan, 2007) and JACK^TMIntelligent Agents (JACK) (Agent Oriented Software, 2008a) and design methodologies (Padgham and Winikoff, 2004), reference architectures (Van Brussel et al, 1998) and standards (IEEE, 2006) are beginning to appear. These are all strong indicators of a mature technology. However, the uptake of the technology is not as rapid or as pervasive as its advocates have expected. It has been proposed as becoming the paradigm of choice for the development of complex distributed systems (Decker et al, 2004) and as the heir apparent to object oriented programming (Wooldridge, 2002). Is intelligent agent technology simply in need of the killer application, or are there more fundamental reasons as to why a technology that promises so much has not taken the world by storm? What does the future hold for the technology?

We choose to use the definition of agency proposed in (Wooldridge, 2002), namely that an agent is a computer program capable of acting autonomously according to the input from the environment in order to achieve its design objectives. We then define an intelligent agent as one that determines its actions through an explicit reasoning process. In a holon, this reasoning process is structured so that a holon can be part of a larger whole, while also being a selfcontained entity in its own right. From a software engineering perspective, one would expect to gain major benefits from intelligent agent technology through its deployment in complex distributed applications such as web development, behaviour modeling, virtual enterprise management and the management of sensor networks.