Gaining wide acceptance for the use of agents in industry requires both relating it to the nearestantecU3O1 teccU3O1 (objec t-oriented software development) and usingartifac2 to support the development environment throughout the full systemlifec34I1 We address both of these requirements in this paper by desc51U"3 some of the mostcstU2 requirements for modeling agents and agent-based systems---using a set of UML idioms and extensions. This paper illustrates theapproac by presenting a three-layer AUML representation for agent interacOU" protocO andcdUO6521 byinc14O4U other useful agent-based extensions to UML.

Gaining wide acceptance for the use of agents in industry requires both relating it to the nearest antecedent technology (objectoriented software development) and using artifacts to support the development environment throughout the full system lifecycle. We address both of these requirements using AUML, the Agent UML (Unified Modeling Language)—a set of UML idioms and extensions. This paper illustrates the approach by presenting a three-layer AUML representation for agent interaction protocols: templates and packages to represent the protocol as a whole; sequence and collaboration diagrams to capture inter-agent dynamics; and activity diagrams and state charts to capture both intra-agent and inter-agent dynamics.

From a software engineering perspective, agent systems are a specialization of object-oriented (OO) systems, inwE2] individual objects have theirow threads of control and their ow goals or sense of purpose. Engineering such systems is most naturally approached as an extension of object-oriented systems engineering. In particular, the Unified Modeling Language (UML) can be naturally extended to support the distinctive requirements of multi-agent systems. One such requirement results from the increasing emphasis on the correspondencebetwsp multi-agent systems and social systems. Sociological analogies are proving fruitful models for agent-oriented constructions,wons sociologists increasingly use agents as a modeling tool for studying social systems. We combine several existing organizational models for agents, including AALAADIN, dependency theory, interaction protocols, and holonics, in a general theoretical framework, and show how UML can be applied and extended to capture constructions in that framework.

This article discusses our current research directions and preliminary results in each of these areas. Theory and tools for agent communication

Software agents are currently the subject of much research in many interrelated fields. Unfortunately, there has not been enough emphasis on defining the techniques required to build practical agent systems. While many agent researchers refer to tasks, few really define what they mean. Tasks not only define the internal processing an agent must perform, but also how interactions with other agents relate to internal processes. 1.

Agent technologies have steadily matured in moving from the research laboratory to industrial application over the last ten years. Numerous systems have been deployed or are under advanced development with strong industrial support. These systems suggest important lessons for both industry and researchers. From an industrial perspective, these examples reflect trends in both business and technology that make agents an increasingly attractive commercial tool. From a research perspective, these examples identify important gaps in agent technology that merit the attention of academicians.

Abstract. Exploring agent conversation in the context of fine-grained agent coordination research has raised several intellectual questions. The major issues pertain to interactions between different agent conversations, the representations chosen for different classes of conversations, the explicit modeling of interactions between the conversations, and how to address these interactions. This paper is not so ambitious as to attempt to address these questions, only frame them in the context of quantified, scheduling-centric multi-agent coordination research. 1

This paper describes an approach that enables agents to execute any interaction protocol that can be expressed in the proposed XML representation. Therefore, agents will be capable of executing any protocol representation received in run-time. In our approach, explicitly represented protocols are converted in an agent internal structure more suitable for being processed than XML. The internal representation of the protocol is converted to a set of production rules that control the behaviour of the agent according to the protocol. The used XML representation, which closely mirrors AUML protocol diagrams, is defined by an XML Schema.

It is anticipated that the UML, perhaps with domain-specific extensions, will increasingly be used to model and analyse agent-based systems. Current commercial tools for UML, however, contain a number of gaps that limit this growth potential. As an example, there is little or no support for automatic translations between UML notations. We present one such translation --- from sequence diagrams to statecharts --- and discuss how such an algorithm could be used in agent modeling.

This paper describes a traffic surveillance system as a particular case of the class of intelligent distributed dynamic-information systems (IDDIS). The Traffic Surveillance System is a vision-based FIPA compliant multi-agent system that uses the FIPA Agent Communication Language (ACL) and the FIPA Semantic Language (SL). The focus of the work is inter-agent communication and coordination. We have extended the SL expressiveness with respect to the representation of uncertainty and to the representation of ad hoc MPEG7 descriptions. We propose a transport encoding format more suitable for time-constrained systems than the original textual format proposed in the FIPA specifications. We show that, within the scope of the FIPA platform, the FIPA ACL is a communication language powerful enough to achieve multi-agent coordination through communication. This work also suggests that the FIPA platform is suitable for building surveillance based applications.