Software and knowledge... In this article, we argue that intelligent agents and agent-based systems offer novel opportunities for developing effective tools and techniques. Following a discussion on the classic subject of what makes software complex, we introduce intelligent agents as software structures capable of making "rational decisions". Such rational decision-makers are well-suited to the construction of certain types of software, which mainstream software engineering has had little success with. We then go on to examine a number of prototype techniques proposed for engineering agent systems, including formal specification and verification methods for agent systems, and techniques for implementing agent specifications

Abstract not found

In this paper, we introduce a vision for Semantic Web services which combines the growing Web services architecture and the Semantic Web and we will propose DAML-S as a prototypical example of an ontology for describing Semantic Web services. Furthermore, we show that DAML-S is not just an abstract description, but it can be efficiently implemented to support capability matching and to manage interaction between Web services. Specifically, we will describe the implementation of the DAML-S/UDDI Matchmaker that expands on UDDI by providing semantic capability matching, and we will present the DAML-S Virtual Machine that uses the DAML-S Process Model to manage the interaction with Web service. We will also show that the use of DAML-S does not produce a performance penalty during the normal operation of Web services. © 2003 Elsevier B.V. All rights reserved.

Abstract. Software engineers continually strive to develop tools and techniques to manage the complexity that is inherent in software systems. In this article, we argue that intelligent agents and multi-agent systems are just such tools. We begin by reviewing what is meant by the term “agent”, and contrast agents with objects. We then go on to examine a number of prototype techniques proposed for engineering agent systems, including methodologies for agent-oriented analysis and design, formal specification and verification methods for agent systems, and techniques for implementing agent specifications. 1

In the past, research on agent-oriented software engineering had been widely lacking touch with the world of industrial software development. Recently, a cooperation has been established between the Foundation of Intelligent Physical Agents (FIPA) and the Object Management Group (OMG) aiming to increase acceptance of agent technology in industry by relating to de facto standards (object-oriented software development) and supporting the development environment throuDoRHk44Duu4DuDuwDu As a first resuDW of this cooperation, we proposed AGENT UML [Bau er, 1999; Odell 2000], an extension of the Unified Modeling langung (UML), a de facto standard for object-oriented analysis and design. In this paper, we describe the heart of AGENT UML, i.e., mechanisms to model protocols for muWfkFUDo interaction.Particuio UML extensions described in this paper incluD protocol diagrams, agent roles, mus,DHUvk4Do lifelines, extended UML message semantics, nested and interleaved protocols, and protocol templates.

We present a logic-based formalism for modeling of dialogues between intelligent and autonomous software agents, building on a theory of abstract dialogue games which we present. The formalism enables representation of complex dialogues as sequences of moves in a combination of dialogue games, and allows dialogues to be embedded inside one another. The formalism is computational and its modular nature enables dierent types of dialogues to be represented.

. To solve complex problems, agents work cooperatively with other agents in heterogeneous environments. We are interested in coordinating the local behavior of individual agents to provide an appropriate system-level behavior. The use of intelligent agents provides an even greater amount of flexibility to the ability and configuration of the system itself. With these new intricacies, software development is becoming increasingly difficult. Therefore, it is critical that our processes for building the inherently complex distributed software that must run in this environment be adequate for the task. This paper introduces a methodology for designing these systems of interacting agents. 1.

To gain wider acceptance for the use of agents in industry, it is a necessity to relate it to the nearest antecedent technology (object-oriented software development) and to introduce appropriate artifacts to support the development environment throughout the full system life cycle. We address both of these requirements by presenting agent UML, the Agent UML (Unified Modeling Language) — a set of UML idioms and extensions. This paper provides an agent UML representation of the internal behavior of an agent; it then relates this internal description to the external behavior of the agent by using and extending UML class diagrams and by describing agent interaction protocols in a new way. Our claim is that by extending the de-facto standard representation for object-oriented modeling to agents, the learning curve for object-oriented developers to adopt aspects of agent-based programming becomes much less steep. Thus, agentoriented programming as a whole will become more amenable to mainstream software engineering.

Abstract—This paper surveys and analyzes the state of the art of agent-mediated electronic commerce (e-commerce), concentrating particularly on the business-to-consumer (B2C) and business-to-business (B2B) aspects. From the consumer buying behavior perspective, agents are being used in the following activities: need identification, product brokering, buyer coalition formation, merchant brokering, and negotiation. The roles of agents in B2B e-commerce are discussed through the business-to-business transaction model that identifies agents as being employed in partnership formation, brokering, and negotiation. Having identified the roles for agents in B2C and B2B e-commerce, some of the key underpinning technologies of this vision are highlighted. Finally, we conclude by discussing the future directions and potential impediments to the wide-scale adoption of agent-mediated e-commerce. Index Terms—Agent-mediated electronic commerce, intelligent agents. 1

Open systems are characterized by heterogeneous participants which can enter or leave the system at will. Typical examples are e-commerce applications or information agent systems. Agents (e.g. personal assistants for buying things on the Internet) will only temporarily take up roles (e.g. a buyer in on-line auctions). This creates the need to define precisely what it means that an agent "takes up" a role and "enacts" it. In this paper we present ongoing research on the determination of the conditions under which an agent can enact a role and what it means for the agent to enact a role. We define possible relations between roles and agents and discuss architectural and functional changes that an agent must undergo when it enters an open agent system.