AI'2004 was held at the University of Western Ontario in London, Ontario from May 17 to May 19, 2004. The conference was held jointly with the Computer and Robot Vision and Graphics Interface conferences. The three conferences attracted more than 200 attendees. Three workshops and a graduate symposium were held in conjunction with the technical sessions. Three preconference workshops were affiliated with AI'2004: The Third Business Agents and the Semantic Web workshop, organized by Harold Boley, Scott Buffett, Bruce Spencer (National Research Council), Ali Ghorbani (University of New Brunswick), and Said Tabet (Macgregor Inc.); the First Agent Meets Robot workshop, organized by Hamada Ghenniwa, (University of Western Ontario), Weiming Shen (National Research Council) and Mohamed Kamel (University of Waterloo); and the First Causality and Causal Discovery workshop, organized by Kamran Karimi (University of Regina).

Developing agents that could perceive the world, reason about what they perceive in relation to their own goals and acts, has been the Holy Grail of AI. Early attempts at such holistic intelligence (for example, SRI International's AI researchers turned their attention to component technologies for structuring a single agent, such as planning, knowledge representation, diagnosis, and learning. Although most of AI research was focused on single-agent issues, a small number of AI researchers gathered at the Massachusetts Institute of Technology Endicott House in 1980 for the First Workshop on Distributed AI. The main scientific goal of distributed AI (DAI) is to understand the principles underlying the behavior of multiple entities in the world, called agents and their interactions. The discipline is concerned with how agent interactions produce overall multiagent system (MAS) behavior.

The Fourth International and Interdisciplinary Conference on Modeling and Using Context (CONTEXT-03) took place at the Stanford University Center for the Study of Language and Information in Stanford, California, on 23 to 25 June 2003. Like the previous conferences, CONTEXT-03 fulfilled its aim of bringing together representatives of many different research areas, spanning the whole range of the cognitive and information sciences, and with interests ranging from the use of context in specific, commercial applications to highly general philosophical, psychological, and logical theories. The conference chair was Fausto Giunchiglia, University of Trento. The program chairs were Patrick Blackburn, INRIA Lorraine; Chiara Ghidini, the Centre for Scientific and Technological Research in Trento; and Roy Turner, University of Maine. There were 77 submissions, from which 31 papers and 14 posters were selected. One of the aims of the CONTEXT conferences is to bring together representatives of ...

This article summarizes 16 agent strategies that were designed for the 2002 Trading Agent Competition. Agent architects use numerous general-purpose AI techniques, including machine learning, planning, partially observable Markov decision processes, Monte Carlo simulations, and multiagent systems. Ultimately, the most successful agents were primarily heuristic based and domain specific. It would be quite a daunting task to manually monitor prices and make bidding decisions at all web sites currently offering the camera--especially if accessories such as a flash and a tripod are sometimes bundled with the camera and sometimes auctioned separately. However, for the next generation of trading agents, autonomous bidding in simultaneous auctions will be a routine task.

Much of the economic value of electronic commerce comes from the automation of interactions between businesses and individuals. Game theory is a useful set of tools that can be used by designers of electronic-commerce applications in analyzing and engineering of automated agents and communication protocols. The central theoretical concept used in game theory is the Nash equilibrium. In this article, I show how the outcomes supported by a Nash equilibrium can positively be enlarged using automated negotiations. In addition, despite the sharp falls in the share prices of many "dotcoms" since early 2000, electronic commerce is still likely to have a major and lasting effect on most forms of economic activities.

As a field, knowledge representation has often been accused of being off in a theoretical noman's land, removed from, and largely unrelated to, the central issues in AI. This article argues that recent trends in KR instead demonstrate the benefits of the interplay between science and engineering, a lesson from which all AI could benefit. This article grew out of a survey talk on the Third International Conference on Knowledge Representation and Reasoning (KR '92) (Nebel, Rich, and Swartout 1992) that I presented at the Thirteenth International Joint Conference on Artificial Intelligence (IJCAI '93). This article is an edited version of a talk surveying that conference, which I presented at the Thirteenth International Joint Conference on Artificial Intelligence (IJCAI '93). Although nominally a conference overview, the article attempts to summarize the state of the conference and the field with respect to the intertwined goals of science and engineering.

The innovative reapplication of a multiagent system for human-in-the-loop (HIL) simulation was a consequence of appropriate agent-oriented design. The use of intelligent agents for simulating human decision making offers the potential for analysis and design methodologies that do not distinguish between agent and human until implementation. With this as a driver in the design process, the construction of systems in which humans and agents can be interchanged is simplified. Two systems have been constructed and deployed to provide defense analysts with the tools required to advise and assist the Australian Defense Force in the conduct of maritime surveillance and patrol. The experiences gained from this process indicate that it is simpler, both in design and implementation, to add humans to a system designed for intelligent agents than it is to add intelligent agents to a system designed for humans.

The Second International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS-03) was held in Melbourne, Australia, in July 2003. Attracting nearly 500 delegates, the event confirmed AAMAS as the academic main event for researchers with an interest in multiagent systems. We summarize the conference highlights and report on the associated workshops, tutorials, and emerging trends. Although a number of workshops had been held more or less regularly since 1980 (notably the U.S.-based Distributed Artificial Intelligence workshop series), until the mid-1990s, there was no dedicated archival venue for agentrelated work. By 2000, the situation had changed dramatically; by then, there were two major conferences, a major international workshop, and a dedicated journal, all publishing work in the agents area. Although all these venues were doing good business (there was no shortage of submitted papers), the overheads involved in organizing three major events--not to mention the ...

People often act together with a shared purpose; they collaborate. Collaboration enables them to work more efficiently and to complete activities they could not accomplish individually. An increasing number of computer applications also require collaboration among various systems and people. Thus, a major challenge for AI researchers is to determine how to construct computer systems that are able to act effectively as partners in collaborative activity. Collaborative activity entails participants forming commitments to achieve the goals of the group activity and requires group decision making and group planning procedures.

Agent-based systems technology has generated lots of excitement in recent years because of its promise as a new paradigm for conceptualizing, designing, and implementing software systems. This promise is particularly attractive for creating software that operates in environments that are distributed and open, such as the internet. Currently, the great majority of agent-based systems consist of a single agent. However, as the technology matures and addresses increasingly complex applications, the need for systems that consist of multiple agents that communicate in a peer-topeer fashion is becoming apparent. Central to the design and effective operation of such multiagent systems (MASs) are a core set of issues and research questions that have been studied over the years by the distributed AI community.