Intelligent Assistants Working With You and For You
AITopics > Agents
Authors have agents . . . professional athletes have agents . . . movie stars have agents . . . and you have agents too. Because an agent is someone with expertise who is entrusted to go out and act on your behalf, the computer programs that help you to maximize your computing experiences are called "agents". The next time that you search for specific information on the internet, picture your own agent or group of agents at work, with each knowing just what you're interested in and how important your time is.
Definition of the Area
From Sec. 1.3 of Poole & Mackworth Artificial Intelligence: Foundations of Computational Agents (2010):
"A coupling of perception, reasoning, and acting comprises an agent. An agent acts in an environment. An agent's environment may well include other agents. An agent together with its environment is called a world.
An agent could be, for example, a coupling of a computational engine with physical sensors and actuators, called a robot, where the environment is a physical setting. It could be the coupling of an advice-giving computer--an expert system--with a human who provides perceptual information and carries out the task. An agent could be a program that acts in a purely computational environment--a software agent. "
Good Places to Start
Is There an Intelligent Agent in Your Future? By James A. Hendler. Nature Web Matters (March 11, 1999). This wonderful paper received the AAAI-2000 Effective Expository Writing Award.
Agent Based Computing by Michael Luck, GEOconnexion International Magazine, May 2006 . "Agents can be defined to be autonomous, problem-solving computational entities capable of effective operation in dynamic and open environments. They are often deployed in environments in which they interact, and sometimes cooperate, with other agents (including both people and software) that have possibly conflicting aims. These environments are known as multi-agent systems. Since agents are autonomous entities capable of exercising choice over their actions and interactions, act to achieve individual objectives, they cannot, therefore, be directly invoked but can be assigned tasks by their owners."
AI and Agents: State of the Art. By Eduardo Alonso. AI Magazine 23(3): Fall 2002, 25-30. "This article is a reflection on agent-based AI. My contention is that AI research should focus on interactive, autonomous systems, that is, agents. Emergent technologies demand so. We see how recent developments in (multi-) agent-oriented research have taken us closer to the original AI goal, namely, to build intelligent systems of general competence. Agents are not the panacea though. I point out several areas such as design description, implementation, reusability, and security that must be developed before agents are universally accepted as the AI of the future."
Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents (1996). Stan Franklin and Art Graesser. In Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages, Springer-Verlag. " An autonomous agent is a system situated within and a part of an environment that senses that environment and acts on it, over time, in pursuit of its own agenda and so as to effect what it senses in the future. ... Suppose we wished to classify software agents further. How might we go about it? The major subclassification schemes that come to mind are via control structures, via environments (database, file system, network, Internet), via language (in which written) or via applications. Each might be useful. ..."
Best-kept secret agent revealed - No longer just the province of specialist sectors, agent-based computing is changing the way systems interact and how they are managed. By Boris Sedacca. ComputerWeekly.com (October 12, 2006). "Agent-based computing has already transformed processes such as automated financial markets trading, logistics, and industrial robotics. Now it is moving into the mainstream commercial sector as more complex systems with many different components are used by a wider range of businesses. Organisations that have successfully implemented agent technologies include DaimlerChrysler, IBM and the Ministry of Defence. So what are agent technologies? In essence, they are autonomous software systems that can decide for themselves what they need to do. Agents are capable of operating in dynamic and open environments and often interact with other agents - including both people and software. 'Agents are a way to manage interactions between different kinds of computational entities, and to get the right kind of behaviour out of large-scale distributed systems,' says Michael Luck of the School of Electronics and Computer Science at the University of Southampton and executive director of the EU-funded AgentLink [see below] action co-ordination programme."
Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents. By Stan Franklin and Art Graesser, Institute for Intelligent Systems, University of Memphis. From Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages, Springer-Verlag, 1996. Abstract: "The advent of software agents gave rise to much discussion of just what such an agent is, and of how they differ from programs in general. Here we propose a formal definition of an autonomous agent which clearly distinguishes a software agent from just any program. We also offer the beginnings of a natural kinds taxonomy of autonomous agents, and discuss possibilities for further classification. Finally, we discuss subagents and multiagent systems."
Logical Agents. Chapter 7 of the textbook, Artificial Intelligence: A Modern Approach (Second Edition), by Stuart Russell and Peter Norvig. "We begin in Section 7.1 with the overall agent design. Section 7.2 introduces a simple new environment, the wumpus world, and illustrates the operation of a knowledge-based agent without going into any technical detail. Then, in Section 7.3, we explain the general principles of logic. Logic will be the primary vehicle for representing knowledge throughout Part III of the book."
Computational Intelligence - A Logical Approach. David Poole, Alan Mackworth and Randy Goebel. Oxford University Press, New York (1998). "The focus is on an intelligent agent acting in an environment. We start with simple agents acting in simple, static environments and gradually increase the power of the agents to cope with more challenging worlds. We make this concrete by repeatedly illustrating the ideas with three different agent tasks: a delivery robot, a diagnostic assistant, and an information slave (the infobot). " - from the Preface.
The Many Faces of Agents. By Katia P. Sycara. AI Magazine 19(2): Summer 1998, 11-12. This article introduces the Intelligent Agents special issue of AI Magazine. Articles include: Autonomous Agents as Synthetic Characters by Elliott and Brzezinski (agents that project believable, engaging personae); Constraints and Agents by Eaton, Freuder and Wallace; and Multiagent Systems by Sycara.
Biological and Social Models of Intelligence: Agents Theories. Section 1.1.4 of Chapter One (available online) of George F. Luger's textbook, Artificial Intelligence: Structures and Strategies for Complex Problem Solving, 5th Edition (Addison-Wesley; 2005). "What are the main themes supporting an agent-oriented and emergent view of intelligence? They include: 1. Agents are autonomous or semi-autonomous. ... 2. Agents are 'situated.' ... 3. Agents are interactional. ... 4. The society of agents is structured. ... 5. Finally, the phenomenon of intelligence in this environment is 'emergent.' ... Based on these observations, we define an agent as an element of a society that can perceive (often limited) aspects of its environment and affect that environment either directly or through cooperation with other agents."
Agents of Cooperation - Orchestrating the actions of mobile snippets of smart software. By Ivars Peterson. Science News (January 2, 1999). "Allowing agents to act on their own is a key requirement. [Pattie] Maes and her colleagues define an autonomous agent as a 'computational system' that can inhabit a complex, constantly changing environment, sense what is going on, and act independently to accomplish a specified set of tasks or achieve certain goals. The underlying software technology is an offshoot of research in artificial intelligence. A software agent often makes inferences on the basis of a set of rules specifying its actions in a variety of situations."
Electric Elves: Applying Agent Technology to Support Human Organizations. By H. Chalupsky, Y. Gil, C. A. Knoblock, K. Lerman, J. Oh, D. V. Pynadath, T. A. Russ, and M. Tambe. Information Sciences Institute, University of Southern California. To appear in Proceedings of the Thirteenth Annual Conference of Innovative Applications of Artificial Intelligence (IAAI-2001), Seattle, WA, August 2001. Excerpt from the abstract: " The operation of a human organization requires dozens of everyday tasks to ensure coherence in organizational activities, to monitor the status of such activities, to gather information relevant to the organization, to keep everyone in the organization informed, etc. Teams of software agents can aid humans in accomplishing these tasks, facilitating the organization’s coherent functioning and rapid response to crises, while reducing the burden on humans. Based on this vision, this paper reports on Electric Elves, a system that has been operational, 24/7, at our research institute since June 1, 2000."
"Intelligent agent" technology staging a comeback. By Paul Festa. CNET (October 28, 1999). "Consumer confusion about agents is no fluke: The category encompasses such a wide range of products and technologies that even developers disagree over what the term means. Artificial intelligence academics despair over arriving at a universally agreed-upon definition, but among software sellers the term generally is used to denote software that automates certain computing functions and exercises some judgment on the user's behalf."
Towards a Standardization of Multi-Agent System Frameworks. Roberto A. Flores-Mendez. (1999). Crossroads. "It is important that agents not only have ontologies to conceptualize a domain, but also that they have ontologies with similar constructions."
IDA, a Software Agent Cognitive System. By Stan Franklin. ERCIM News (No. 53; April 2003). "This IDA technology is based on a host of disparate mechanisms taken from the 'new' artificial intelligence. These include the Hofstadter and Mitchell's Copycat architecture, Kanerva's sparse distributed memory, Maes' behavior nets, and Jackson's pandemonium theory. IDA is currently up and running, and has been tested to the satisfaction of Navy detailers. Watching IDA in action, their reaction is typically a nod of the head together with 'Yes, that's how I do it.'"
Pattie - MIT professor Pattie Maes has created a stir by making agents a household word.... By Marguerite Holloway. Wired (December 1997; Issue 5.12). "In the past two years, Maes and Firefly have done more for software agents than the semi-intelligent bits of software have ever done for us. Agents - small programs that do electronic tasks for their masters and that can, ideally, learn by watching their user's activities - have been dogged by hype for the past 20 years. The approach that AI researchers had generally used - the deliberative thinking paradigm - had not yielded serviceable autonomous agents, so the promise of the servile bots was never followed by the real thing. Now, however, agents are finding their way into the world in large part because of Maes's pioneering work. Her radical approach flew in the face of traditional knowledge-based AI research."
Dependable Agent Systems. IEEE Intelligent Systems Special Issue (Volume 19, Number 5; September/October 2004). "It is well known that building dependable software systems for dynamic environments is difficult. It is also well known that building large-scale distributed software systems is difficult. The relatively few attempts to combine these two tasks confirm that successfully building large-scale distributed systems with predictable dependability properties is exceptionally difficult. The articles in this special issue of IEEE Intelligent Systems deal with this issue and discuss an emerging and exciting new approach to building these most challenging kinds of systems. " - Abstract: Guest Editors' Introduction.
The Ghost in Your Machine - Computers may soon monitor your work, notice when fatigue sets in, and fix mistakes. BusinessWeek Online Reporter Olga Kharif interviews Chris Forsythe (August 25, 2003). "At their most benign, smart computers seem like executive secretaries for those of us who can't afford one -- offering tremendous advances in productivity. Yet some fear that the concept suggests an ominous encroachment out of a sci-fi movie. Cognitive psychologist Chris Forsythe, who leads the Sandia team, insists that the machines are designed to augment -- not replace -- human activity. 'We don't want to take the human out of the loop,' he says."
A Web Page for Teleo-Reactive Programs. Provided by Nils J. Nilsson, Kumagai Professor of Engineering, Emeritus, Robotics Laboratory, Department of Computer Science, Stanford University. "A teleo-reactive (T-R) program is a mid-level agent control program that robustly directs an agent toward a goal in a manner that continuously takes into account the agent's changing perceptions of a dynamic environment. T-R programs are written in a production-rule-like language and require a specialized interpreter." Web site with demo programs and bibliography on T-R programs
Pattie Maes on Software Agents: Humanizing the Global Computer. Interviewed by Charles Petrie and Meredith Wiggins. IEEE Internet Computing Online; Vol. 1, No. 4 (1994). "
Robot Telescopes Comb the Skies. By Lakshmi Sandhana. Wired News (September 21, 2004). "British astronomers have just begun to operate RoboNet-1.0, a global network of the world's biggest robotic telescopes, controlled by intelligent software to effectively act as one giant eye that can be focused anywhere in the sky within a minute. ... ESTAR, a joint project of Liverpool John Moores University and Exeter University, developed intelligent autonomous software programs, known as agents, that will function as the brains of the network. Acting as 'virtual astronomers,' the agents will collect and analyze data 24 hours a day, alerting their flesh-and-blood counterparts only when they catch sight of something noteworthy."
Persistent Assistants: Living and Working with AI: Papers from the 2005 Spring Symposium, ed. Daniel Shapiro, Pauline Berry, John Gersh, Nathan Schurr. Technical Report SS-05-05. American Association for Artificial Intelligence, Menlo Park, California.
Human Responsibility for Autonomous Agents. By Ben Shneiderman. IEEE Intelligent Systems 22(2): March/April 2007, 60-61. Abstract: "Automated or autonomous systems can sometimes fail harmlessly, but they can also destroy data, compromise privacy, and consume resources, such as bandwidth or server capacity. What's more troubling is that automated systems embedded in vital systems can cause financial losses, destruction of property, and loss of life. Controlling these dangers will increase trust while enabling broader use of these systems with higher degrees of safety. Obvious threats stem from design errors and software bugs, but we can't overlook mistaken assumptions by designers, unanticipated actions by humans, and interference from other computerized systems. This article is part of a special issue on Interacting with Autonomy."
Persistent Assistants: Living and Working with AI: Papers from the 2005 Spring Symposium, ed. Daniel Shapiro, Pauline Berry, John Gersh,and Nathan Schurr. Technical Report SS-05-05. American Association for Artificial Intelligence, Menlo Park, California.
Intelligent Agents for Interactive Simulation Environments. By Milind Tambe, W. Lewis Johnson, Randolph M. Jones, Frank Koss, John E. Laird, Paul S. Rosenbloom, and Karl Schwamb. AI Magazine 16(1): Spring 1995, 15-39. Interactive simulation environments are rich domains for investigating intelligent automated agents, with requirements for integration of many agent capabilities but without the costs and demands of perceptual processing or robotic control. This project is aimed at developing humanlike, intelligent agents that can interact with each other, as well as with humans, in such virtual environments.
Privacy-Aware Autonomous Agents for Pervasive Healthcare. By Monica Tentori, Jesus Favela, and Marcela D. Rodríguez. IEEE Intelligent Systems (November/December 2006; 21(6): 55-62. "Pervasive technology in hospital work raises important privacy concerns. Autonomous agents can help developers design privacy-aware systems that handle the threats raised by pervasive technology."
Agents of Change - Autonomous agents are still in the labs but could eventually play a critical role in areas ranging from setting market prices to creating more resilient networks. By Patrick Thibodeau. Computerworld (September 6, 2004). "Over the past year, NASA has been uploading software into the Earth Observing-1 satellite, turning it into a testbed for autonomous agents. The agents -- software programs that are able to learn and can function independently -- are used to manage experiments and operate the spacecraft. The effort is part of a technology initiative that researchers say will reshape IT over the course of many years. Autonomous agents have the potential to become an extraordinarily powerful technology, with the capacity to learn, experiment and act independent of human control. Agents could ultimately improve productivity, increase software reliability and change the operation of markets, particularly supply chains."
Tutorial Slides & Notes
Tutorial on Voting Theory. Ulle Endriss (ILLC, University of Amsterdam). 24th AAAI Conference on Artificial Intelligence (AAAI-2010), Atlanta, 12 July 2010. Abstract: "Voting theory is the study of methods for conducting elections. It has attracted a lot of interest from AI researchers in recent years: there are important applications of voting theory in AI (for example, in multiagent systems) and the tools and techniques of AI have proven useful for the study of voting methods (for example, complexity theory, knowledge representation, and automated reasoning). This tutorial will provide an introduction to the theory of voting for AI researchers. We will present the most important voting procedures and cover some of the classical theorems in the field. "
AI on the Web: Intelligent Agents, the resource companion to the textbook, Artificial Intelligence: A Modern Approach (Second Edition), by Stuart Russell and Peter Norvig, with links to reference material, people, research groups, books, companies and much more.
"Agent Construction Tools. This page provides a survey of agent construction tools. The tools are categorized as either commercially available products or academic and research projects." From AgentBuilder. Also be sure to see their introduction to agent technology: Why, When, and Where to Use Software Agents.
"AgentLink is a coordinating organisation for research and development activities in the area of agent-based computer systems funded by the European Commission." Resources include:
Autonomous Remote Agent. From NASA's site devoted to the Deep Space 1 spacecraft. "...an artificial intelligence system was placed on board to plan and execute spacecraft activities. In contrast to remote control, this sophisticated set of computer programs acts as an agent of the operations team on board the remote spacecraft. Rather than have humans do the detailed planning necessary to carry out desired tasks, remote agent will formulate its own plans, using high level goals provided by the operations team....Remote agent, like the other high-risk technologies that have now been tested on DS1, promises to make space exploration of the future more productive and more exciting while staying within NASA's limited budget."
CALO: Cognitive Assistant that Learns and Organizes. "SRI International is leading the development of new software that could revolutionize how computers support decision-makers. The Defense Advanced Research Projects Agency (DARPA), under its Perceptive Assistant that Learns (PAL) program, has awarded SRI the first two phases of a five-year contract to develop an enduring personalized cognitive assistant. ... The software, which will learn by interacting with and being advised by its users, will handle a broad range of interrelated decision-making tasks that have in the past been resistant to automation. It will have the capability to engage in and lead routine tasks, and to assist when the unexpected happens. To focus the research on real problems and to ensure the software meets requirements such as privacy, security, and trust, the CALO project researchers will themselves use the technology during its development."
"The Intelligent Software Agents Lab at Carnegie Mellon University's Robotics Institute envisions a world in which autonomous, intelligent software programs, known as software agents, undertake many of the operations performed by human users of the World Wide Web, as well as a multitude of other tasks." - from the Introduction.
Interesting AI Demos and Projects. Maintained by Charles Dyer, University of Wisconsin. Describes projects involving agents in health information systems, web searching, personal shopping, and more.
Knowledge Rich Intelligent Agents at Soar Technology, Inc.: "Achieving human-level reasoning and decision-making for autonomous systems requires agents that are capable of reasoning through large volumes of knowledge. A key element is the ability to resolve conflicts, solve problems, and operate in ambiguous and uncertain situations in the same way as a human expert. To be truly useful, these agents must also be able to interact with humans and other agents in natural ways, communicating in domain-specific languages and explaining their behaviors when required. At Soar Technology, we develop these agents for use in training systems, exploratory experimentation, and for embedded control of unmanned and robotic systems."
TAC, the Trading Agent Competition "is an international forum designed to promote and encourage high quality research into the trading agent problem."
Other References Offline
Agre, P. E. 1995. Computational Research on Interaction and Agency. Artificial Intelligence 72: 1-52.
Bradshaw, Jeffrey, editor. 1997. Software Agents. Cambridge, MA: AAAI Press/MIT Press.
Demazeau, Yves, editor. 1998. Proceedings of the Third International Conference on Multiagent Systems. Menlo Park, CA: AAAI Press.
Ferber, Jacques. 1998. Multi-Agent Systems: Towards a Collective Intelligence. Reading, MA: Addison-Wesley.
Flynn, Julie. 1997. Edinburgh: Where Ersatz Crickets Chirp. Business Week (June 23, 1997): 100.
Huhns, Michael N., and Munindar P. Singh, editors. 1997. Readings in Agents. San Francisco: Morgan Kaufmann.
Lesser, Victor, editor. 1995. Proceedings of the First International Conference on Multiagent Systems. Menlo Park, CA: AAAI Press.
Lyons, Daniel. 1997. The Buzz About Firefly. New York Times Magazine (June 29, 1997): 36-37+.
Maes, Patti. 1994. Agents that Reduce Work and Information Overload. Communications of the ACM, Vol. 37, No. 7. Available to subscribers for free, others for a fee.
Maes, Patti., editor. 1990. Designing Autonomous Agents: Theory and Practice From Biology to Engineering and Back. Cambridge, MA: MIT Press.
Nilsson, Nils J. 1998. Artificial Intelligence: A New Synthesis. San Francisco: Morgan Kaufmann. Approaches the field of AI by looking at the construction of more and more complex agents.
Pollack, Martha. 1992. The Uses of Plans. Artificial Intelligence 57: 43-68. From the IJCAI-91 Computers and Thought Lecture.
Tokoro, Mario, editor. 1996. Proceedings of the Second International Conference on Multiagent Systems. Topics include coordination, distributed planning, implementing multi-agent systems, market-oriented approaches, multiagent applications, multiagent learning, multiagent search, mutual knowledge, negotiation, organizational aspects, real-world agents, situated agents, sociability, and teams of agents. Menlo Park, CA: AAAI Press.