Agent software is a rapidly developing area of research. However, the overuse of the word ‘agent ’ has tended to mask the fact that, in reality, there is a truly heterogeneous body of research being carried out under this banner. This overview paper presents a typology of agents. Next, it places agents in context, defines them and then goes on, inter alia, to overview critically the rationales, hypotheses, goals, challenges and state-of-the-art demonstrators of the various agent types in our typology. Hence, it attempts to make explicit much of what is usually implicit in the agents literature. It also proceeds to overview some other general issues which pertain to all the types of agents in the typology. This paper largely reviews software agents, and it also contains some strong opinions that are not necessarily widely accepted by the agent community. 1 1

The multi-agent systems approach of knowledge level co-operation between autonomous agents promises significant benefits to distributed systems engineering, such as enhanced interoperability, scalability and reconfigurability. However, thus far, because of the innate difficulty of constructing multi-agent systems, this promise has been largely unrealised. Hence, there is an emerging desire amongst agent developers to move away from developing point solutions to point problems in favour of developing methodologies and toolkits for building distributed multi-agent systems. This philosophy led to the development of the ZEUS Agent Building Toolkit, which facilitates the rapid development of collaborative agent applications through the provision of a library of agent-level components and an environment to support the agent building process. The ZEUS toolkit is a synthesis of established agent technologies with some novel solutions to provide an integrated collaborative agent building enviro...

There is an emerging consensus on the need to develop methodologies and tool-kits for building distributed multi-agent systems. This paper presents ZEUS, an advanced development tool-kit for constructing collaborative agent applications. ZEUS is a culmination of a careful synthesis of established agent technologies with the addition of some new ones, to provide an integrated environment for the rapid software engineering of collaborative agent applications. ZEUS defines a multi-agent system design methodology, supports the methodology with an environment for capturing user specification of agents, and automatically generates the executable source code of the user-defined agents. We also report on preliminary informal evaluation of ZEUS on three domains. Keywords Agent architectures, distributed multi-agent systems, constructing collaborative agent applications. I. Introduction This paper describes ZEUS, an advanced tool-kit for building distributed multi-agent applications. The too...

Agent systems must have a strong foundation; one approach that has been successfully applied to other kinds of software is patterns. This paper presents a collection of patterns for agents. 2. MOTIVATION Almost all agent development to date has been "home grown" [4] and done from scratch, independently, by each development team. This has led to the following problems: . Lack of an agreed definition: Agents built by different teams have different capabilities. . Duplication of effort: There has been little reuse of agent architectures, designs, or components. . Inability to satisfy industrial strength requirements: Agents must integrate with existing software and computer infrastructure. They must also address security and scaling concerns. Agents are complex and ambitious software systems that will be entrusted with critical applications. As such, agent based systems must be engineered with valid software engineering principles and not constructed in an ad hoc fashion. Agent system...

Researchers working with vast quantities of information in a geographically distributed manner are often confronted with problems of finding relevant information as well as colleagues with related interests. The MEMOIR project aims at assisting this collaboration by applying agent technology to user trails and documents. MEMOIR is an open architecture based on the existing Web infrastructure; in contrast to the Web, we treat links and trails as first class objects. Agents mine users' trails and links and also perform resource discovery tasks such as searching the Web. This paper describes the design, communication mechanism and implementation of the MEMOIR agent system which is currently being trialed in three end-user organisations. 1 Introduction Finding people with similar interests can be as difficult as efficiently accessing documents with related information. This is especially true for research oriented, globally distributed organizations such as pharmaceutical compan...

Agent-based architectures are an effective method for constructing open, dynamic, distributed information systems. The KRAFT system exploits such an architecture, focusing on the exchange of information -- in the form of constraints and data -- among participating agents. The KRAFT approach is particularly wellsuited to solving design and configuration problems, in which constraints and data are retrieved from agents representing customers and vendors on an extranet network, transformed to a common ontology, and processed by mediator agents. This paper describes the KRAFT system, discusses the issues involved in joining a KRAFT network from the point-of-view of information providers in Cyberspace, and examines the role of autonomous and mobile agents in KRAFT.

In this dissertation, we present a novel approach for the automatic composition of Web services on the envisioned Semantic Web. Automatic service composition requires dealing with three major research thrusts: semantic description of Web services, composability of participant services, and generation of composite service descriptions. We first propose an ontology-based framework for organizing and describing semantic Web services. We introduce the concept of community to cluster Web services based on their domain of interest. Each community is defined as an instance of an ontology called community ontology. We then propose a composability model to check whether semantic Web services can be combined together, hence avoiding unexpected failures at run time. The model defines formal safeguards for meaningful composition through the use of composability rules. We also introduce the notions of composability degree and τ-composability to cater for partial and to-tal composability. Based on the composability model, we propose a set of algorithms that automatically generate detailed descriptions of composite services from high-level specifications of composition requests. We introduce a Quality of Composition (QoC) model to assess the quality of the generated composite services. The tech-niques presented in this dissertation are implemented in WebDG, a prototype for accessing e-government Web services. Finally, we conduct an extensive performance study (analytical and experimental) of the proposed composition algorithms.

Factory and Factory Method patterns [11] are used together to form the Plan and Intention Factory, as shown in Figure 5. The PlanFactory is abstract; it provides the interface to create the ActionPlan objects. The ConcretePlanFactory provides the implementation to create the ConcretePlans. For this it uses the Library which stores several ActionPlan classes and instantiates the requested one. This plan object is then used by the IntentionThread. Per the Factory Method pattern, ReactionIntention or CollaborationIntention subclasses will be instantiated depending on the ActionPlan type. Both of these define the virtual methods of the IntentionThread class. These methods are used by the IntentionThread class for creating the respective intention thread objects, letting the subclasses determine how an object is to be instantiated. 6.5 THE PRIORITIZER Problem How can priority handling and other forms of behavior be added to an intention dynamically ? Forces . There are two main Intentio...

There is an emerging consensus on the need to develop tool-kits for building distributed multi-agent systems. This paper outlines ZEUS, an advanced development tool-kit for constructing collaborative agent applications. ZEUS is a culmination of a careful synthesis of established agent technologies with the addition of some new ones, to provide an integrated environment for the rapid software engineering of collaborative agent applications. Keywords Agent architectures, distributed multi-agent systems, constructing collaborative agent applications. I. Introduction This paper describes ZEUS, an advanced tool-kit for building distributed multi-agent applications. The tool-kit facilitates the construction of collaborative agent applications, arguably one of the more complex of agent types because they can have rich, deliberative internal models and operate in open and time-constrained environments (Nwana 1996). The reasons for the development of ZEUS fall into two broad categories. First...

One of the potential applications for agent-based systems is m-commerce. A lot of research has been done on making such systems intelligent to personalize their services for users. In most systems, user-supplied keywords are generally used to help generate profiles for users. In this paper, an evolutionary ontology-based product-brokering agent has been designed for m-commerce applications. It uses an evaluation function to represent a user’s preference instead of the usual keyword-based profile. By using genetic algorithms, the agent tracks the user’s preferences for a particular product by tuning some parameters inside its evaluation function. A prototype called “Handy Broker ” has been implemented in Java and the results obtained from our experiments looks promising for m-commerce use.