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

ion and delegation: Agents can be made extensible and composable in ways that common iconic interface objects cannot. Because we can "communicate" with them, they can share our goals, rather than simply process our commands. They can show us how to do things and tell us what went wrong (Miller and Neches 1987). . Flexibility and opportunism: Because they can be instructed at the level of 16 BRADSHAW goals and strategies, agents can find ways to "work around" unforeseen problems and exploit new opportunities as they help solve problems. . Task orientation: Agents can be designed to take the context of the person's tasks and situation into account as they present information and take action. . Adaptivity: Agents can use learning algorithms to continually improve their behavior by noticing recurrent patterns of actions and events. Toward Agent-Enabled System Architectures In the future, assistant agents at the user interface and resource-managing agents behind the scenes will increas...

Agents can personalize otherwise impersonal computational systems. The World Wide Web presents the same appearance to every user regardless of that user’s past activity. Web Browser Intelligence (WBI, pronounced “WEB-ee”) is an implemented system that organizes agents on a user’s workstation to observe user actions, proactively offer assistance, modify web documents, and perform new functions. WBI can annotate hyperlinks with network speed information, record pages viewed for later access, and provide shortcut links for common paths. In this way, WBI personalizes a user’s web experience by joining personal information with global information to effectively tailor what the user sees.

tication involves "service performing" agents, which execute a well defined task at the request of a user (eg find me the cheapest flight to Paris or arrange a meeting with the managing director some day next week). Finally, there are "predictive" agents, which volunteer information or services to a user, without being explicitly asked, whenever it is deemed appropriate (eg an agent may monitor newsgroups on the INTERNET and return discussions that it believes to be of interest to the user or a holiday agent may inform its user that a travel firm is offering large discounts on holidays to South Africa knowing that the user is interested in safaris). Common to all these classes are the following key hallmarks of agenthood (Wooldridge and Jennings, 1995): . Autonomy: agents should be able to perform the majority of their problem solving tasks without the direct intervention of humans or other agents, and they should have a degree of contro

this paper we present the distributed system architecture, agent collaboration interactions, and a reusable set of software components for structuring agents. The system architecture has three types of agents: Interface agents interact with the user receiving user specifications and delivering results. They acquire, model, and utilize user preferences to guide system coordination in support of the user's tasks. Task agents help users perform tasks by formulating problem solving plans and carrying out these plans through querying and exchanging information with other software agents. Information agents

As the Web continues to evolve, the sophistication of the programs that are employed in interacting with it will also increase in sophistication. Web agents, programs acting autonomously on some task, are already present in the form of spiders. Agents offer substantial benefits and hazards, and because of this, their development must involve not only attention to technical details, but also the ethical concerns relating to their resulting impact. These ethical concerns will differ for agents employed in the creation of a service and agents acting on behalf of a specific individual. An ethic is proposed that addresses both of these perspectives. The proposal is predicated on the assumption that agents are a reality on the Web, and that there are no reasonable means of preventing their proliferation. 1 -- Introduction The ease of construction and potential Internet-wide impact of autonomous software agents on the World Wide Web [1] has spawned a great deal of discussion and occasional c...

Abstract. In this paper, we sketch a model of what people do when they search for information on the web. From a theoretical perspective, our interest lies in the cognitive processes and internal representations that are both used in and affected by the search for information. From a practical perspective, our aim is to provide personal support for informationsearching and to effectively transfer knowledge gained by one person to another. Toward these ends, we first collected behavioral data from people searching for information on the web; we next analyzed these data to learn what the searchers were doing and thinking; and we then constructed specific web agents to support searching behaviors we identified. 1

This paper discusses the design space of believable social robots. We synthesise ideas and concepts from areas as diverse as comics design and rehabilitation robotics. First, we revisit the work of the Japanese researcher Masahiro Mori in the context of recent developments in social robots. Next, we discuss work in the arts into comics design, an area which has dealt for decades with the problem of creating believable characters. Finally, in order to illustrate some of the important issues involved we focus on a particular application area: the use of interactive robots in autism therapy, work that is carried out in the Aurora project. We discuss design issues of social robots in the context of `design spaces' and `niche spaces', concepts that have been defined originally for intelligent agent architectures [26] but which, we propose, can be highly valuable for social robotics design. This paper is meant to open up a discussion towards a systematic exploration of design spaces and niche spaces of social robots.

Our study considers children’s perceptions of robots in terms of physical attributes, personality and emotion traits. To examine children’s attitudes towards robots, a questionnaire approach was taken with a large sample of children, followed by a detailed statistical framework to analyse the data. Results show that children clearly distinguish between emotions and behaviour when judging robots. The distinguishing robotic physical characteristics for positive and negative emotions and behaviour are highlighted. Children judge human-like robots as aggressive, but human-machine robots as friendly providing support for the Uncanny Valley. The paper concludes with discussing the results in light of design implications for children’s robots. 1

Because ever more powerful intelligent agents will interact with people in increasingly sophisticated and important ways, greater attention must be given to the technical and social aspects of how to make agents acceptable to people [87]. The technical challenge is to devise a computational structure that guarantees that from