Table of contents: Intelligent Agents. Deductive Reasoning Agents. Practical Reasoning Agents. Reactive and Hybrid Agents. Multiagent Interactions. Reaching Agreements. Communication. Working Together. Methodologies. Applications. Logics for Multiagent Systems.

" The concept of an agent has become important in both Artificial Intelligence (AI) and mainstream computer science. Our aim in this paper is to point the reader at what we perceive to be the most important theoretical and practical issues associated with the design and construction of intelligent agents. For convenience, we divide these issues into three areas (though as the reader will see, the divisions are at times somewhat arbitrary). Agent theory is concerned with the question of what an agent is, and the use of mathematical formalisms for representing and reasoning about the properties of agents. Agent architectures can be thought of as software engineering models of agents; researchers in this area are primarily concerned with the problem of designing software or hardware systems that will satisfy the properties specified by agent theorists. Finally, agent languages are software systems for programming and experimenting with agents; these languages may embody principles proposed by theorists. The paper is not intended to serve as a tutorial introduction to all the issues mentioned; we hope instead simply to identify the most important issues, and point to work that elaborates on them. The article includes a short review of current and potential applications of agent technology. "

" It is by now a cliché that there is no one, universally accepted definition of intelligent agent technology, but a number loosely related techniques. And yet there are certain themes that appear common to agent-based systems, and correspondingly, certain problems that must be addressed and overcome by all agent system builders. The aim of this paper is to briefly survey the tools and techniques that can be used to address these common issues, and that hence form a substrate for software agent systems. We begin with a review of agent communication languages, focusing particularly on the emerging standard known as KQML. We then present a thumbnail sketch of various programming languages for building agent-based systems, and go on to discuss support for ontologies, which allow agents to communicate using commonly-defined terms and concepts. We then consider other computing infrastructure support for agent-based systems, in particular, the use of client-server architectures and distributed object frameworks. Finally, we present some general comments and conclusions. "

" According to Webster’s dictionary an agent is: 1. a person or thing that acts or brings about a certain result 2. one who is empowered to act for another The first part of the definition could include almost any software or hardware device and is not restricted to anything that the AI in Medicine community is interested in. The second part is more suggestive though the concept is not at all precise. Because the idea of an “agent” is somewhat vague it is now common to define agents in terms of their typical characteristics. Caglayan and Harrison identify the characteristic features of agents of the second type as entities that:

perform tasks (on behalf of users or other agents)

interact with users to receive instructions and give responses

operate autonomously without direct intervention by users, including monitoring the environment and acting upon the environment to bring about changes

show intelligence – to interpret monitored events and make appropriate decisions.

" AgentLink has produced a consultation report outlining the current situation with respect to the status of agent technologies and indicating key directions for future development of the field. "

" Multi-agent systems are one of the most exciting research areas in artificial intelligence (AI) at the moment. A multi-agent system is a collection of independent agents that communicate in order to co-operate in the joint resolution of a complex task. An agent may be defined as an autonomous software entity that receives inputs and interacts with its environment, performing tasks in the pursuit of a set of goals. Although there does not exist a universally accepted definition of the term agent, it is normally assumed that its behaviour should be autonomous (it must control its internal state and take its own decisions), flexible (it has to adapt dynamically to changes in its environment), proactive (it may take the initiative when appropriate and perform actions not explicitly required by the user) and intelligent (by applying AI reasoning and learning techniques). In the last 5 years there has been a growing interest in the application of agent-based systems in health care, and some specialised workshops in this topic are beginning to appear. ... "

" Confidentiality constraints often preclude the release of disaggregate data about individuals, which limits the types and accuracy of the results of geographical health analyses that could be done. Access to individually geocoded (disaggregate) data often involves lengthy and cumbersome procedures through review boards and committees for approval (and sometimes is not possible). Moreover, current data confidentiality-preserving solutions compatible with fine-level spatial analyses either lack flexibility or yield less than optimal results (because of confidentiality-preserving changes they introduce to disaggregate data), or both. In this paper, we present a simulation case study to illustrate how some analyses cannot be (or will suffer if) done on aggregate data. We then quickly review some existing data confidentiality-preserving techniques, and move on to explore a solution based on software agents with the potential of providing flexible, controlled (software-only) access to unmodified confidential disaggregate data and returning only results that do not expose any person-identifiable details. The solution is thus appropriate for micro-scale geographical analyses where no person-identifiable details are required in the final results (i.e., only aggregate results are needed). Our proposed software agent technique also enables post-coordinated analyses to be designed and carried out on the confidential database(s), as needed, compared to a more conventional solution based on the Web Services model that would only support a rigid, pre-coordinated (pre-determined) and rather limited set of analyses. The paper also provides an exploratory discussion of mobility, security, and trust issues associated with software agents, as well as possible directions/solutions to address these issues, including the use of virtual organizations. Successful partnerships between stakeholder organizations, proper collaboration agreements, clear policies, and unambiguous interpretations of laws and regulations are also much needed to support and ensure the success of any technological solution. "

" In this paper, a multiagent system (MAS) is presented, aiming to enhance monitoring, surveillance, and educational services of a generic medical contact center (MCC) for chronic disease management. In such a home-care scenario, a persistent need arises for efficiently monitoring the patient contacts and the MCC's functionality, in order to effectively manage and interpret the large volume of medical data collected during the patient sessions with the system, and to assess the use of MCC resources. Software agents were adopted to provide the means to accomplish such real-time information-processing tasks, due to their autonomous, reactive and/or proactive nature, and their effectiveness in dynamic environments by incorporating coordination strategies. Specifically, the objective of the MAS is to monitor the MCC environment, detect important cases, and inform the healthcare and administrative personnel via alert messages, notifications, recommendations, and reports, prompting them for actions. The main aim of this paper is to present the overall design and implementation of a proposed MAS, emphasizing its functional model and architecture, as well as on the agent interactions and the knowledge-sharing mechanism incorporated, in the context of a generic MCC. "

" The Independent LifeStyle Assistant (I.L.S.A.) is an agent-based monitoring and support system to help elderly people to live longer in their homes by reducing caregiver burden. I.L.S.A. is a multiagent system that incorporates a unified sensing model, situation assessments, response planning, real-time responses and machine learning. This paper describes the some of the lessons we learned during the development and six-month field study ... [From Conclusion:] I.L.S.A., in its form as an agent-based system, has been retired. Using an agent-based system, contrary to our expectations, significantly added to the development effort. I.L.S.A. had many capabilities that needed to be centralized, and therefore it is clear to us that pursuing a simpler route would have saved us time, money, and frustration—a singlethreaded, component-oriented architecture may have been a better approach...