In this paper we present sofar, a versatile multi-agent framework designed for Distributed Information Management tasks. sofar embraces the notion of proactivity as the opportunistic reuse of the services provided by other agents, and provides the means to enable agents to locate suitable service providers. The contribution of sofar is to combine some ideas from the distributed computing community with the performative-based communications used in other agent systems: communications in sofar are based on the startpoint/endpoint paradigm, which is the foundation of Nexus, the communication layer at the heart of the Computational Grid. We explain the rationale behind our design decisions, and describe the predefined set of agents which make up the core of the system. Two distributed information management applications have been written, a general query architecture and an open hypermedia application, and we recount their design and operations.

Links are the key element for changing a text into a hypertext, and yet the WWW provides limited linking facilities. Modelled on Open Hypermedia research the Distributed Link Service provides an independent system of link services for the World-Wide Web and allows authors to create configurable navigation pathways for collections of WWW resources. This is achieved by adding links to documents as they are delivered from a WWW server, and by allowing the users to choose the sets of links that they will see according to their interests. This paper describes the development of the link service, the facilities that it adds for users of the WWW and its specific use in an Electronic Libraries project. Key words: Links, hypertext, open hypermedia, link services, authoring, HTTP proxies. 1 1. INTRODUCTION TO LINK SERVICES Hypertext environments have always provided more functionality than word-processors, and the hyper- part of the environment has been in the form of links. Links are the co...

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...

A multiagent framework has been developed to address distributed multimedia information management. Our particular interest is information management within organisations, where information is a vital resource and locating the right information at the right time is a critical problem. Hence our focus is navigation assistance, and we are pursuing the idea that information acquired by one user navigating the information space is something that can be utilised to assist other users. The design of the system we present builds on the experiences of an earlier project which provided navigation assistance based on information about which documents other users had visited; our system has an improved architecture and extends the functionality, focusing on bookmarks instead of 'trails'. We have also integrated additional services including handling of multimedia documents and integration with other open hypermedia systems. The system is being evaluated within commercial organisations. ...

versatile multi-agent framework designed for Distributed Information Management tasks. SoFAR embraces the notion of proactivity as the opportunistic reuse of the services provided by other agents, and provides the means to enable agents to locate suitable service providers. The contribution of SoFAR is to combine ideas from the distributed computing community with the performative-based communications used in other agent systems: communications in SoFAR are based on the startpoint/endpoint paradigm, a powerful abstraction that can be mapped onto multiple communication layers. SoFAR also adopts an XML-based declarative approach for specifying ontologies and agents, providing a clear separation with their implementation. We explain the rationale behind our design decisions; we describe two distributed information management applications and we recount their design and operations. 1

In this paper we present a system that attempts to learn the surfing user’s interests without asking him for any feedback. The system uses the user profile to conducts an independent search of the Internet, trying to find pages that the user have not read yet and might find interesting. The system consists of 3 modules: (1) The data-collecting module, which collects the data to be processed into the user’s profile. The collected data is URLs the user reads and e-mail messages the user authorizes the system to process. (2) The user profiling module, which processes the collected data into a user profile, using the clustering method Dynamic Suffix Tree Clustering (DSTC). (3) The search module, which explores the Internet, searching for web sites the profiled user might be interested in. 1.

sofar, the SOuthampton Framework for Agent Research, is used to build a pervasive information system, which provides context-adapted information to mobile users. Mobile agents are used as intermediaries between mobile users and the xed infrastructure, migrating to locations with resources adapted to their objectives. sofar is equipped with an algorithm for tracking mobile agents and for transparently routing messages to them, without assuming the existence of any xed or centralised control. In this paper, we present the algorithm and describe how it was integrated in the declarative style of sofar communications. Then, we present the agent meeting room: the realisation, in the agent framework, of a mechanism by which mobile users may exchange information during meetings. 1

This report presents Plegma, a market-based, network-centric agent architecture to support integrated information processing services in Intranets and Extranets. The Plegma architecture is inherently scalable from secure Intranets to large-scale Internet applications. Distributed autonomous agents, responsible for local resources and specific processing methods, collaborate to decompose complex processing tasks and address dynamically the problem of task allocation and charging. The architecture features a market-based resource management mechanism, supports accounting procedures, enables the continued use of legacy software, and allows the formulation of specific access and charging policies. The report also addresses general development issues and outlines specific implementations of the architecture: a distributed environment for image processing services, and a workflow processing environment for functional integration and process re-engineering in healthcare networks. E. Kaldoudi...