UMBC AgentWeb
UMBC ebiquity | AgentWeb | AgentNews | agents@cs.umbc.edu | FIPA | KQML | Knowledge Sharing | NEW! | Help

Papers on agents available on-line

  • Simulated Social Control for Secure Internet Commerce, Lars Rasmusson Sverker Jansson, Swedish Institute of Computer Science, 1 April, 1996. ABstract: In this paper we suggest that soft security such as social control has to be used to create secure open systems. Social control means that it is the participants themselves who are responsible for the security, as opposed to leaving the security to some external or global authority. Social mechanisms don't deny the existence of malicious participants. Instead they are aiming at avoiding interaction with them. This makes them more robust than hard security mechanisms such as passwords, who reveal everything if they are bypassed. We describe our work in progress of constructing a workbench to run simulations of electronic markets. By examining the success of different security mechanisms to avoid maliciously behaving actors we hope to gain insight into how to create electronic markets. The idea of creating reputations for the participants is discussed. Finally some legal aspects on using social control and reputation as security mechanisms are discussed. 3/5/97

  • The Tenth Knowledge Acquisition for Knowledge-Based Systems Workshop was held in Banff, Canada, on November 9-14, 1996. Some papers relating to agents presented at the conference were: 12/8/96

  • Instructible agents: Software that just keeps getting better, H. Lieberman and D. Maulsby, IBM Systems Journal, Vol. 35, Nos. 3&4, 1996. Agent software is a topic of growing interest to users and developers in the computer industry. Already, agents and wizards help users automate tasks such as editing and searching for information. But just as we expect human assistants to learn as we work with them, we will also come to expect our computer agents to learn from us. This paper explores the idea of an instructible agent that can learn both from examples and from advice. To understand design issues and languages for human-agent communication, we first describe an experiment that simulates the behavior of such an agent. Then we describe some implemented and ongoing instructible agent projects in text and graphic editing, World Wide Web browsing, and virtual reality. Finally, we analyze the trade-offs involved in agent software and argue that instructible agents represent a ``sweet spot'' in the trade-off between convenience and control. 11/24/96

  • For want of a bit the user was lost: Cheap user modeling J. Orwant, IBM Systems Journal, Vol. 35, Nos. 3&4, 1996. The more a computer knows about a user, the better it can serve that user. But there are different styles, and even philosophies, of how to teach our computers about us--about our habits, interests, patterns, and preferences. ``Cheap'' user modeling, the subject of this essay, simply means ascertaining a few bits of information about each user, processing that information quickly, and providing the results to applications, all without intruding upon the user's consciousness. In short, there are techniques for personalization that can--and should--be built into today's systems. Like most journal papers, this is a description of an existing system: DOPPELG€NGER. But it is also an exhortation for readers to incorporate the described techniques and philosophy into their own systems. 11/24/96

  • Zlotkin, G. and Rosenschein, J.S. (1996), "Mechanisms for Automated Negotiation in State Oriented Domains", Journal of AI Research, Volume 5, pages 163-238. Abstract: This paper lays part of the groundwork for a domain theory of negotiation, that is, a way of classifying interactions so that it is clear, given a domain, which negotiation mechanisms and strategies are appropriate. We define State Oriented Domains, a general category of interaction. Necessary and sufficient conditions for cooperation are outlined. We use the notion of worth in an altered definition of utility, thus enabling agreements in a wider class of joint-goal reachable situations. An approach is offered for conflict resolution, and it is shown that even in a conflict situation, partial cooperative steps can be taken by interacting agents (that is, agents in fundamental conflict might still agree to cooperate up to a certain point).

    A Unified Negotiation Protocol (UNP) is developed that can be used in all types of encounters. It is shown that in certain borderline cooperative situations, a partial cooperative agreement (i.e., one that does not achieve all agents' goals) might be preferred by all agents, even though there exists a rational agreement that would achieve all their goals.

    Finally, we analyze cases where agents have incomplete information on the goals and worth of other agents. First we consider the case where agents' goals are private information, and we analyze what goal declaration strategies the agents might adopt to increase their utility. Then, we consider the situation where the agents' goals (and therefore stand-alone costs) are common knowledge, but the worth they attach to their goals is private information. We introduce two mechanisms, one 'strict', the other 'tolerant', and analyze their affects on the stability and efficiency of negotiation outcomes. 10/29/96

  • Do-I-Care: A Collaborative Web Agent, Brian Starr, Mark S. Ackerman, and Michael Pazzani, Proceedings of the ACM CHI'96 Conference, April, 1996. Abstract: Social filtering and collaborative resource discovery mechanisms often fail because of the extra burden, even tiny, placed on the user. This work proposes an innovative World Wide Web agent that uses a model of collaboration that leverages the natural incentives for individual users to easily provide for collaborative work. 10/13/96

  • Auto-FAQ: an experiment in cyberspace leveraging , Steven D. Whitehead, GTE Laboratories Incorporated. Abstract "... This paper explores the idea of harnessing computer networks to overcome the knowledge acquisition bottleneck. We introduce the idea of a CYLINA (CYberspace Leveraged INtelligent Agent) --- an intelligent system that gains knowledge/information through interactions with a large population of network users. Instead of depending on the big efforts of a few knowledge engineers, CYLINAs rely on small, incremental contributions from a global population of experts. Our thesis is that the shear volume of interaction will allow significant knowledge to be acquired in a short amount of time. ... A version of Auto-FAQ is currently operating on a private network at GTE Laboratories. The system is currently able to answer basic questions about itself, WWW, and Mosaic. Future plans are to make Auto-FAQ and its associated software available on the global Internet."10/13/96

  • Beehive: A system for cooperative filtering and sharing of information, Bernardo A. Huberman and Michael Kaminsky, Xerox PARC, August, 1996, (9 pages). Abstract: We have designed and implemented a distributed system for social sharing and filtering of information. It relies on the automatic recording of the behavior and interactions of members of communities of practice. The system automatically updates membership in informal communities at regular intervals and provides a simple and intuitive interface for distributing relevant information among its members. 10/1/96

  • An Information Mediator Network for Tasks in Dynamic Environments , Ramesh Patil, Weixiong Zhang and Wei-Min Shen, USC Information Sciences Institute. Abstract: Coordination of activities among information workers and services, tracking and managing activities, and intelligent distribution of information are essential to the efficient operation of any large enterprise. This is particularly important in the health-care domain, where many different organizations must cooperate to provide patient care reliably in a dynamically changing environment. In this paper we present a distributed system that supports cooperative problem solving, activity management, and intelligent delivery of information in dynamic and unreliable environments. The system consists of a network of task/context managers (TCMs). Each TCM manages a group of related agents. It maintains up-to-date information on availability, operational status, and activities of participating agents, and it acts as a mediator between service requesters and service providers. In addition, the TCM acts as a representative for its agents with other TCMs allowing different groups of agents to collaborate with one anothers. This paper describes the system architecture, its implementation and capabilities including matchmaking, plan monitoring and failure recovery. Our system has been used in prehospital emergency patient information management applications. 8/31/96

  • Some recent papers from CMU include:
    • Katia Sycara, Keith Decker, Anandeep Pannu, Mike Williamson, and Dajun Zeng. Distributed Intelligent Agents. Submitted to IEEE Expert, July, 1996.
    • Keith Decker, Anandeep Pannu, Katia Sycara, and Mike Williamson. Designing Behaviors for Information Agents. Submitted to First International Conference on Autonomous Agents (AGENTS-97), July, 1996.
    • Keith Decker, Mike Williamson, and Katia Sycara. Matchmaking and Brokering. To appear in Proceedings of the Second International Conference on Multi-Agent Systems (ICMAS-96), 1996.
    8/12/96

  • Staffan Haegg and Fredrik Ygge, Agent-Oriented Programming in Power Distribution Automation - An Architecture, a Language, and their Applicability, Ph.L. thesis, Lund University, Sweden, 1995. Abstract: "Power Distribution Automation and Demand Side Management (DA/DSM) are the concepts of automating power distribution and providing customer services. ... In the thesis, we identify the need for system integration, high-level cooperation protocols (e.g., protocols for negotiation), powerful and flexible models of interaction, minimizing of communication needs, and a robust system behaviour when computing is heavily distributed. We describe how Agent-Oriented Programming (AOP) can be used to address the problems listed above. Existing multiagent system (MAS) contributions are examined, and our agent architecturethe (DA-SoC) and our agent language (DAAL) are presented and analyzed. A DA-SoC agent is procedural and goal-driven, and it holds a world model in declarative form. It has a programmable model of interaction that allows a programmer to tailor its interactive behaviour. Agent interaction in DA-SoC is tightly connected to the agent execution, which leads to the concept of semantic addressing and the notion of DA-SoC as a computational model for distributed computing. Agents can be given specific roles in a society, and joint goals and joint action can be realized. ...". 8/10/96

  • ACACIA: An Agency Based Collaboration Framework for Heterogenous Multiagent Systems, Wilfred C. Jamison, Syracuse University. Abstract: We introduce our framework called ACACIA for distributed problem solving by multiple agents. While most efforts in multi-agent systems (MAS) focus on homogenous agents, we acknowledge the need for a higher level framework. The issue on interoperability among various frameworks is addressed. We design a system whereby a group of heterogenous agents can collaborate in solving a problem without having to re-engineer the individual agents. This paper gives a macro-level description of our framework which is based mainly on the notion of agencies. We also apply a case-based coordination scheme in which a database of collaboration protocols is consulted for the given problem situation. First, we give our own view of agent and then present agency as our metaphor for agent organization. The rest of the paper will discuss ACACIA's problem solving paradigm and runtime system.7/22/96

  • Hongjun Song, Stan Franklin, and Aregahegn Negatu, SUMPY: A Fuzzy Software Agent, Proceedings of the international conference on intelligent systems, Reno, Nevada, June 19-21, 1996. Abstract: SUMPY is a software agent "living" in and helping to maintain a UNIX file system for better disk space utilization by compressing and backing up files. Built using subsumption architecture, SUMPY displays a "plug and play" preperty. A new UNIX maintenance task can be added to SUMPY's repertoire without modification of existing layers. One of SUMPY's layers sports a fuzzy control mechanism enabling it to achieve its goals in a real-world manner. Another restricts SUMPY's activity to times of slow CPU use. An experiment in agent architecture and in the use of agents for such maintenance tasks, SUMPY promises to prove useful, and has added no significant problems to the test systems. 7/21/96

  • Thesis: Björn Hermans, "Intelligent Software Agents on the Internet: an inventory of currently offered functionality in the information society & a prediction of (near-)future developments" is now available on the World Wide Web.", Tilburg University, Tilburg, The Netherlands. Abstract: Software agents are a rapidly developing area of research. However, to many it is unclear what agents are and what they can (and maybe cannot) do. In the first part, this thesis will provide an overview of these, and many other agent-related theoretical and practical aspects. Besides that, a model is presented which will enhance and extend agents' abilities, but will also improve the way the Internet can be used to obtain or offer information and services on it. The second part is all about trends and developments. On the basis of past and present developments of the most important, relevant and involved parties and factors, future trends and developments are extrapolated and predicted. 9/9/96

  • Paper: What sort of architecture is required for a human-like agent?, Aaron Sloman, The University of Birmingham. Invited talk at Cognitive Modeling Workshop, AAAI96, Portland Oregon, Aug 1996. Abstract: This paper is about how to give human-like powers to complete agents. For this the most important design choice concerns the overall architecture. Questions regarding detailed mechanisms, forms of representations, inference capabilities, knowledge etc. are best addressed in the context of a global architecture in which different design decisions need to be linked. Such a design would assemble various kinds of functionality into a complete coherent working system, in which there are many concurrent, partly independent, partly mutually supportive, partly potentially incompatible processes, addressing a multitude of issues on different time scales, including asynchronous, concurrent, motive generators. Designing human like agents is part of the more general problem of understanding design space, niche space and their interrelations, for, in the abstract, there is no one optimal design, as biological diversity on earth shows. 7/7/96

  • Paper: Brafman, R.I. and Tennenholtz, M. (1996), "On Partially Controlled Multi-Agent Systems", JAIR, Volume 4, pages 477-507. Available as brafman96a.ps (356K) or brafman96a.ps.Z (146K). Abstract: Motivated by the control theoretic distinction between controllable and uncontrollable events, we distinguish between two types of agents within a multi-agent system: controllable agents, which are directly controlled by the system's designer, and uncontrollable agents, which are not under the designer's direct control. We refer to such systems as partially controlled multi-agent systems, and we investigate how one might influence the behavior of the uncontrolled agents through appropriate design of the controlled agents. In particular, we wish to understand which problems are naturally described in these terms, what methods can be applied to influence the uncontrollable agents, the effectiveness of such methods, and whether similar methods work across different domains. Using a game-theoretic framework, this paper studies the design of partially controlled multi-agent systems in two contexts: in one context, the uncontrollable agents are expected utility maximizers, while in the other they are reinforcement learners. We suggest different techniques for controlling agents' behavior in each domain, assess their success, and examine their relationship. 7/1/96

  • Paper: Nigel Jacobs and Ray Shea, The Role of Java in InfoSleuth: Agent-based Exploitation of Heterogeneous Information Resources, Microeclectronics and Computer Technology Corporation (MCC), Austin, Texas, 1996. Abstract: "...InfoSleuth is a consortial research project at MCC which is developing technologies for addressing these issues. Based on MCC's successful Carnot project, InfoSleuth is developing a network of semi-autonomous software agents which perform semantic data integration and retrieval across a widely distributed network environment. To achieve this, the project employs recent advances in ontology management, data mining, workflow automation, object brokering and language translation. The InfoSleuth architecture consists of agents communicating with each other via the high-level language KQML. Queries are specified in the flexible knowledge representation language KIF, with respect to common ontologies that are managed in knowledge-base management systems such as Ontolingua and CLIPS. The queries are routed by mediation and brokerage agents to specialized agents for data retrieval from distributed resources, and for integration and analysis of results. User interaction with this web of agents is via a personalized intelligent user agent which communicates with the user via Java applets running inside a Java-capable Web browser such as Netscape." 6/23/96

  • Paper: Cooperation-Ware: Integration OF Human Collaboration WITH Agent-Based Interaction, Gerd Völksen, Hans Haugeneder, Alex Jarczyk, Peter Löffler, Siemens AG, Corporate Research and Development, Munich, Germany. Abstract: This paper presents a platform that integrates cooperation facilities for the most important types of interaction. These include explicit informal human interaction by speech and gestures and implicit semi-formal human interaction referring to an object of common interest. Furthermore, human - application interaction and inter-application interaction is facilitated by agentification of the involved software components utilizing techniques from distributed artificial intelligence (DAI). Particularly, interaction between humans and applications requires specific components referred to as user agents. Cooperation-Ware is a framework for integrating software components supporting all of the above types of communication. It includes audio/video conferencing and tele-pointing, data and application sharing, and agents as well as user agents. The functionality is based on a formal model specifying cooperative actions executed by humans or agents. The Cooperation-Ware framework provides a user interface with an overall interaction methodology based on a room metaphor. The architecture relies on the client-server concept supporting synchronous, asynchronous, and autonomous cooperative work. 6/18/96

  • A Common Agent Platform , Jim White, General Magic, 11 March 1996. Submitted to the Joint W3C/OMG Workshop on Distributed Objects and Mobile Code. 6/3/96 Coordination without Communication , Stan Franklin, University of Memphis, 1996. Abstract: Here we examine situations in which coordinated behaviors occur without prior planning via communication. Such situations are both common and effective in multi-agent systems, be they biological or computational. Such coordination results from stigmergic sampling of the environment and responding to it. We conclude that stigmergic coordination without communication should be considered as a control architecture when designing multi-agent systems. 6/2/96

  • Internet Consultant: An Integrated Conversational Agent for Internet Exploration, Mitsuyuki Inaba, University of Hawaii at Manoa. Abstract: Internet Consultant (IC) is a natural language system that helps the user to explore the internet resources. Externally IC behaves as a conversational agent that assists World Wide Web browsing. Internally it is a multi-agent system which consists of the following three agents; 1) Natural language interface (NLI) agent that understands user's utterance and extracts his/her goals, 2) Planning agent that generates and executes plans to achieve the goals, and 3) Information agent that chooses appropriate information resources on the Internet and retrieves required information from the resources. Since IC utilizes local databases as well as resources provided on the Internet as knowledge bases, theoretically it has unlimited knowledge bases. 6/1/30

  • Ontology-Based Knowledge Discovery on the World-Wide Web. Sean Luke, Lee Spector, and David Rager. To appear in the AAAI96 Workshop on Internet-based Information Systems, 1996. Also available in Gzipped PostScript Format (.ps.gz). Abstract: This paper describes SHOE, a set of Simple HTML Ontology Extensions. SHOE allows World-Wide Web authors to annotate their pages with ontology-based knowledge about page contents. We present examples showing how the use of SHOE can support a new generation of knowledge-based search and knowledge discovery tools that operate on the World-Wide Web. paper web ontology 5/30/96

  • Paper: The Role of Brokers in Electronic Commerce, Paul Resnick, MIT's The Center for Coordination Science (CCS) 5/27/96

  • Paper, Communication: Multi-Agent System Protocol Language Specification, Alejandro Quintero, MarAa Eugenia Ucr"s and Silvia Takahashi, Universidad de los Andes. Abstract: " ... The language described in this article allows the specification of different interaction protocols that may have entities which belong to a multi-agent modeled system. To show an application of the language, we show a system that models the interaction of a research group, where some specific members want to validate or dissolve a hypothesis formulated by an author. This mechanism is represented as a consensual knowledge base. Consensual knowledge bases are supporting tools to exchange ideas and knowledge between group members and/or different groups or entities (researchers, organizations, etc.). ... This language allows the formal design of the interaction protocols between agents, using modal logic operators, world state modeling, and actions' sequentiality and concurrency. 5/19/96

  • Paper: Open Protocol in Multi-agent Systems, Gerard A. W. Vreeswijk, Limburg University, Belgium. Abstract: Protocols for intelligent agents are difficult to write. This is partially because intelligent agents accommodate their interaction to the situation that arises. As a result, the interaction among intelligent agents cannot be governed by a fixed protocol. In this paper I describe an open protocol paradigm for reasoning in a multi-agent system with decentralized control. An open protocol is a collection of rules of interaction that lies open to further alteration and adjustment. I explore the notion of open protocol, and show how it can be altered by rational claims. This may lead to further insights concerning the government of interaction among intelligent agents in multi-agent systems. (compressed postscript) 5/19/96

  • Paper: Self-government in multi-agent systems: experiments and thought-experiments, Gerard A.W. Vreeswijk University of Limburg, Belgium. Abstract: This paper reports on research in self-modifying protocol games. A self-modifying protocol is a set of instructions, rules, or conventions, that can be changed by the systems that communicate with the help of that protocol. The concept is expected to be of great importance for the next generation of intelligent distributed computer systems, such as DPSs, and MASs. This paper tries to show by example that a self-modifying protocol leads to self-governmental behaviour in intelligent distributed computer systems. It further hints at the possible avenues future research might take, and indicates how theoretical results can be obtained. (Postscript) 5/19/96

  • Paper: Distributed Computing: Let Your Agent Handle It, Dan Richman, Techweb, April 17, 1995. Software agents will sweat the details when users lack the time and patience needed to tackle routine and repetitive business chores. 5/18/96

  • Opinion: Voyager: Agents of Alienation, Voyager: Agents of Alienation, by Jaron Lanier. "Here is the opinion: that the idea of "intelligent agents" is both wrong and evil. I also believe that this is an issue of real consequence to the near term future of culture and society. As the infobahn rears its gargantuan head, the agent question looms as a deciding factor in whether this new beast will be much better than TV, or much worse." 5/18/96

  • Paper, IR: Co-operative Information Retrieval in Digital Libraries. Michail Salampasis, John Tait, Chris Bloor, University of Sunderland, UK. Abstract: ... In this paper, we present an open agent-based hypermedia model for distributed digital libraries, but we mainly focus on a technique for using dynamic links, known as co-operative retrieval links, and the implication of this technique for the process and nature of distributed information retrieval.(Postscript). 5/17/96

  • Paper: N. R. Jennings, P. Faratin, M. J. Johnson, P. O'Brien, M. E. Wiegand: "Using Intelligent Agents to Manage Business Processes", Proc. First Int. Conf. on The Practical Application of Intelligent Agents and Multi-Agent Technology (PAAM96),pp. 345-360. London, UK. 5/14/96

  • Paper: Distributed Active Objects, Marc H. Brown and Marc A. Najork, DEC SRC Report #141a, April 15, 1996, 21 pages. Abstract: Many Web browsers now offer some form of active objects, written in a variety of languages, and the number of types of active objects are growing daily in interesting and innovative ways. This report describes our work on Oblets, active objects that are distributed over multiple machines. Oblets are written in Obliq, an object-oriented scripting language for distributed computation. The high-level support provided by Oblets makes it easy to write collaborative and distributed applications. 5/10/96

  • Hyacinth S. Nwana (1996), (postscriptSoftware Agents: An Overview, The Knowledge Engineering Review Vol 11 (3). (postscript 2.6M) Abstract: 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. It places them 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 the 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. [42 pages] 5/9/96

  • Paper: New Fungus Eater Experiments, Thomas Wehrle, Université de Genève, Switzerland. Adapted from: Wehrle, T. (1994). New fungus eater experiments. In P. Gaussier, & J.-D. Nicoud (Eds.), From perception to action (pp. 400-403). Los Alamitos: IEEE Computer Society Press. ABSTRACT: though there seems to be a high agreement among researchers that the concept of autonomous agents should also be applied in Psychology, especially in Emotion Psychology, most work did not exceed the theoretical level yet. One reason obviously is the lack of adequate tools for applying and exploring this concept. This paper describes, on the bases of an implemented software package, what such a tool could look like. This simulation package has already been used for several applications. As an example we discuss an application that implements the basic concepts of the Emotional (or social) Fungus Eater of Masanao Toda. 5/9/96

  • Paper: Simulated Social Control for Secure Internet Commerce, by Lars Rasmusson and Sverker Janson, April 1996. Abstract: In this paper we suggest that soft security such as social control has to be used to create secure open systems. Social control means that it is the participants themselves who are responsible for the security, as opposed to leaving the security to some external or global authority. Social mechanisms don't deny the existence of malicious participants. Instead they are aiming at avoiding interaction with them. This makes them more robust than hard security mechanisms such as passwords, who reveal everything if they are bypassed.

    We describe our work in progress of constructing a workbench to run simulations of electronic markets. By examining the success of different security mechanisms to avoid maliciously behaving actors we hope to gain insight into how to create electronic markets. The idea of creating reputations for the participants is discussed. Finally some legal aspects on using social control and reputation as security mechanisms are discussed. 4/17/96

  • Paper: Personal Security Assistance for Secure Internet Commerce, Andreas Rasmusson and Sverker Janson, April, 1996. Abstract: In this paper we discuss the approach of using a personal security assistant for interacting with mobile agents visiting your computer. We argue that instead of trusting an external authority to guarantee that the agent is correct/benign or that your local resources have all been assigned correct access-restrictions, a more rewarding security policy is to grant the visiting agent access to resources on the assumption that it will do useful work for you and behave as expected.

    Not disqualifying agents from doing useful work for you on the grounds that you have no previous experience from them facilitates the introduction of new agents into the market, since trusting the sender is less crucial.

    The paper contains a discussion on the security approach taken in most of today's agent systems and how security is enforced by Intrusion Detection Systems. We give a rationale for using an interactive Personal Security Assistant as an aid for detecting malicious agents visiting end-user agent environments and sketch the architecture and design criteria of such an assistant. We discuss how malicious programs could be identified and mention some preliminary experiments with Java-applets. 4/17/96

  • Paper: Maksim Tsvetovatyy and Maria Gini, "Toward the Virtual Marketplace - Architectures and Strategies", PAAM96, London, 1996 Abstract: In recent years, many researchers as well as commercial companies have attempted to create intelligent agent-based markets or retail outlets. Unfortunately, most of these systems have fallen short of changing the way commerce is done over the Internet. We think that some of the reasons of this shortfall are an incomplete implementation of the market metaphor and lack of automated purchasing and agent cooperation algorithms. In this research, we attempt to address these problems by designing an open marketplace architecture that includes all elements required for simulating a real market (i.e., communications, goods storage and transfer, banking, administration and policing, etc.). We also address the issues of automated purchasing and agent cooperation by devising strategies and algorithms for them. We also report findings that resulted from implementing and conducting experiments with a free-market agent architecture (MAGMA). MAGMA is an extensible architecture that provides all services essential to agent-based commercial activities. These services are available through an open-standard messaging API, which allows use of a heterogeneous set of agents, independently of platform and language. 4/4/96

  • Paper: Intelligent Agents: A Technology and Business Application Analysis Kathy Heilmann, Dan Kihanya, Alastair Light, and Paul Musembwa. November 1995. 3/31/96

  • Paper: Towards an Active Network Architecture, David L. Tennenhouse and David J. Wetherall, LCS, MIT. Abstract: Active networks allow users to inject customized programs into the nodes of the network. In this paper, we describe our vision of an active network architecture, outline our approach to its design, and survey the technologies that can be brought to bear on its implementation. In the course of this presentation we identify a number of research questions to be addressed and propose that the research community mount a joint effort to develop and deploy a wide area ActiveNet. 3/28/96

  • Paper: From Internet to ActiveNet, D.L. Tennenhouse, S.J. Garland, L. Shrira and M.F. Kaashoek, LCS, MIT. Abstract: ...Active Networks represent a new approach to network architecture that incorporates interposed computation. These networks are "active" in two ways: routers and switches within the network can act on, i.e., perform computations on, user data flowing through them; furthermore, users can "program" the network, by supplying their own programs to perform these computations. ... Our work is motivated by user "pull", as well as technology "push". The "pull" comes from the ad hoc collection of firewalls, Web proxies, multicast routers, mobile proxies, video gateways, etc. that perform user-driven computation at nodes "within" the network. These nodes are flourishing, suggesting user and management demand for their services. One goal of our work is to replace the present collection of ad hoc approaches with a generic capability that allows users to program their networks. The technology "push" is the emergence of "active technologies", supporting the encapsulation, transfer, interposition, and safe and efficient execution of program fragments. Today, active technologies are applied above the end-to-end network layer; for example, to allow clients and servers to exchange program fragments. Our innovation is to leverage and extend these technologies for use within the network - in ways that will fundamentally change today's model of what is "in" the network. 3/28/96

  • Paper: Colusa Software Whitepaper: Omniware: A Universal Substrate for Mobile Code Colusa Software, Pittsburgh PA. Colusa Software's (founded in March 94, acquired by Microsoft in March 96) principal product, Omniware, enables software developers to take code components written in existing programming languages such as C and C++ and create highly efficient, processor-independent client-side components for the Internet and intranet environments. Colusa's unique method for memory protection, known as Software Fault Isolation, allows users to download programs safely from the Internet and run the programs in a fully protected memory space (even when pointers are used). Microsoft plans to incorporate the Colusa technologies in future versions of its Internet and development tools products. 3/28/96

  • Thesis: Beerud Sheth, NEWT: A Learning Approach to Personalized Information Filtering, MIT Media Lab. (also available as Postscript ), 3/20/96

  • Paper: Anthony Chavez and Pattie Maes, Kasbah: An Agent Marketplace for Buying and Selling Goods, PAAM96, 1996. 3/20/96

  • Paper: Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents. Also available as gziped postscript. 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. 3/20/96

  • Paper: Migratory Applications, Krishna A. Bharat and Luca Cardelli, Digital Systems Research Center, Report #138, February 15, 1996. 24 pages. "We introduce a new genre of user interface applications that can migrate from one machine to another, taking their user interface and application contexts with them, and continue from where they left off. Such applications are not tied to one user or one machine, and can roam freely over the network, rendering service to a community of users, gathering human input and interacting with people. We envisage that this will support many new agent-based collaboration metaphors...." 3/10/96

  • PAper: Michael P. Wellman, The Economic Approach to Artificial Intelligence, ACM Computing Surveys Symposium on Artificial Intelligence, September 1995. 2/28/96

  • Paper: Donald McKay, Jon Pastor, Rbon McEntire and Tim Finin, An architecture for information agents, Proceedings of the Third International Conference on Artificial Intelligence Planning Systems (ARPI Supplement), (AIPS-96), AAAI Press, May 1996. 2/13/96

  • IETF draft paper: "Service Location Protocol", J. Veizades, S. Kaplan, E. Guttman, C. Perkins, IETF Service Location Protocol Working Group, 38 pages, 01/23/1996. Abstract: "The service location protocol provides a framework for the discovery and selection of network services. It relies on multicast support at the network layer of the protocol stack it is using. It does not specifically rely upon the TCP/IP protocol stack but makes use of concepts that are found in most TCP/IP protocol implementations. Traditionally, users find services using the name of a network host (a human readable text string) which is an alias for a network address. The service location protocol eliminates the need for a user to know the name of a network host supporting a service. Rather, the user supplies a set of attributes which describe the service. The service location protocol allows the user to bind this description to the network address of the service. Service Location provides a dynamic configuration mechanism for applications in a tightly coupled set of local area networks. It is not a global resolution system for the entire Internet, rather it is intended to serve institutional networks with shared services. 1/24/96

  • Paper: SodaBot: A Software Agent Construction System , Michael Coen, MIT AI Lab. (600K bytes postscript) 1/23/96 .

  • Paper:
  • Constraint Agents for the Information Age Jean-Marc Andreoli, Uwe M. Borghoff, Remo Pareschi and and Johann H. Schlichter. ABSTRACT: We propose constraints as the appropriate computational constructs for the design of agents with the task of selecting, merging and managing electronic information coming from such services as Internet access, digital libraries, E-mail, or on-line information repositories. Specifically, we introduce the framework of Constraint-Based Knowledge Brokers, which are concurrent agents that use so-called _signed feature constraints_ to represent partially specified information and can flexibly cooperate in the management of distributed knowledge. We illustrate our approach by several examples, and we define application scenarios based on related technology such as Telescript and workflow management systems. 1/22/96
  • Intelligent Software Agents is a section of web pages of The Information Worker 2005 Initiative which is "an interactive site dedicated to the exploration of the present and near future of life in the digital world". 1/19/96
  • Edward A. Fox, Electronic librarians, intelligent network agents, and information catalogues (Draft), 1995. 1/19/96
  • There are a number of on-line papers describing the KSL Interactive Ontology Server, including: 1/16/96
  • Joeseph Tardo and Luis Valente. Mobile agent security and Telescript , IEEE CompCon, 1996. 1/16/96
  • Defining the Role of Agents in Web Malls , Robert E. Calem, Web Week, Volume 1, Issue 8, December 1995. This short article discusses the role agents are beginning to play in some on-line shopping sites such as eShop Plaza , Bargain Finder , Internet Fashion Mall , and DreamShop . 12/13/95.
  • Don Gilbert, Manny Aparicio, Betty Atkinson, Steve Brady, Joe Ciccarino, Benjamin Grosof, Pat O'Connor, Damian Osisek, Steve Pritko, Rick Spagna, and Les Wilson, White paper on intelligent agents.IBM Corporation, Research Triangle Park, NC.
  • Cheikes, B. A. (1995) Should ITS Designers Be Looking For A Few Good Agents? In Proceedings of the AI-ED'95 Workshop on Authoring Shells for Intelligent Tutoring Systems, Major, N., Murray, T., and Bloom, C. (eds.). ( PostScript). 11/20/95
  • Cheikes, B. A. (1995) GIA: An Agent-Based Architecture for Intelligent Tutoring Systems. To appear in Proceedings of the CIKM'95 Workshop on Intelligent Information Agents. (in PostScript). 11/20/95
  • James Mayfield, Yannis Labrou, and Tim Finin, Evaluation of KQML as an Agent Communication Language, in Intelligent Agents Volume II -- Proceedings of the 1995 Workshop on Agent Theories, Architectures, and Languages. M. Wooldridge, J. P. Muller and M. Tambe (eds). Lecture Notes in Artificial Intelligence, Springer-Verlag, 1996. 11/7/95
  • Agents, Services, and Market - How do they Integrate. Michael Merz. The paper focuses on the aspect of extending COSM - a flexible CORBA-DII-based Client/Server infrastructure - in order to serve as an agent platform. Petri nets are used as a control flow specification for agents. 11/4/95
  • A Philosophical Encounter, Aaron Sloman,(The University of Birmingham, A.Sloman@cs.bham.ac.uk, http://www.cs.bham.ac.uk/~axs), Proceedings 14th International Joint Conference on AI Montreal, August 1995. -- relates AI to some of the philosophical issues which underly agents (e.g., ontologies, intentionality, etc.). 10/27/95
  • Secret Agents -- A Security Architecture for the KQML Agent Communication Language, Chelliah Thirunavukkarasu (EIT), Tim Finin (UMBC) and James Mayfield (UMBC), October 1995. 200K bytes postscript. (Draft submitted to the CIKM'95 Intelligent Information Agents Workshop, Baltimore, December 1995.)

  • Sánchez, J. A., Azevedo, F. S., and Leggett, J. J. 1995. PARAgente: Exploring the issues in agent-based user interfaces. In Proceedings of the First International Conference on Multi-agent Systems (ICMAS-95), (San Francisco, CA, June) pp. 320-327.
    Paper available in compressed postscript format. 10/22/95
  • Sánchez, J. A., Leggett, J. J., and Schnase J. L. 1994. HyperActive: Extending an open hypermedia architecture to support agency. ACM Transactions on Human-Computer Interaction 1 , 4 (December), 357-382
    Abstract and full paper available in compressed postscript format. 10/22/95
  • Sánchez, J. A. 1994. User agents in the interface to digital libraries. In Proceedings of Digital Libraries '94 (College Station, TX, June), pp. 217-218.
    A position paper , available in compressed postscript format. 10/22/95
  • Maarten Van Dantzich and Trace Wax. Lifelike Computer Characters: the Persona project at Microsoft Research (600KB Microsoft Word format) 10/22/95
  • OAA: An Open Agent Architecture. With P. Cohen, M. Wang & SC Baeg . AAAI Spring Symposium, 1994 PostScript: 55K 9/29/95
  • Making Robots Conscious of their Mental States, John McCarthy, Stanford University. "In AI, consciousness of self consists in a program having certain kinds of facts about its own mental processes and state of mind. We discuss what consciousness of its own mental structures a robot will need in order to operate in the common sense world and accomplish the tasks humans will give it. It's quite a lot. ..." 9/7/95
  • Elephant 2000 - 1992 , John McCarthy, Stanford University. "This unpublished draft is a proposal for a new programming language, but it includes the mathematical theory of computation proposal for distinguishing input-output and accomplishment specifications." 9/7/95

  • Itinerant Agents for Mobile Computing, David Chess, and Benjamin Grosof and Colin Harrison, and David Levine, and Colin Parris,and Gene Tsudik. IEEE Personal Communications Magazine, October 1995. (Sequence listed of authors is alphabetic. Preliminary version is available as IBM Research Report RC20010 (March 1995). IBM T.J. Watson Research Center, Hawthorne, NY 10532. Also available in postscript. 8/16/95

  • An Infrastructure for Mobile Agents: Requirements and Architecture, Anselm Lingnau and Oswald Drobnik, 1995. 8/14/95

  • M. J. Wooldridge and N. R. Jennings, (1995), Intelligent Agents: Theory and Practice, The Knowledge Engineering Review 10 (2) 115-152.

  • Talk to My Agent: Software Agents in Virtual Reality, John Horberg, Computer-Mediated Communication Magazine, v2 n2, Feb. 1, 1995, p.3. 7/13/95.

  • Here Come the Knowbots! by Kevin M. Savetz.

  • Computational Theories of Interaction and Agency -- abstracts for a special double volume of Artificial Intelligence (72(1-2) and 73(1-2), February 1995) edited by Philip E. Agre and Stanley J. Rosenschein. They include 17 papers from a wide variety of disciplines, on the construction of principled characterizations of interactions between agents and their environments, as well as the use of these characterizations to support the explanation of existing agents and the synthesis of new ones.

  • Lenny Foner <foner@media.mit.edu> asks and answers the question What's an Agent, Anyway?. Foner uses Julia, a MUD robot, as an example to define a good software agent and discusses the sociology behind user acceptance of agents. It is also available in Postscript .

  • Are Mobile Agents a Good Idea? , David Chess, IBM Research Report. From the Massively Distributed Systems group at IBM's Thomas J. Watson Research Center.

  • Kuwabara, K., Ishida, T., and Osato, N.: AgenTalk: Coordination Protocol Description for Multiagent Systems , Proc. ICMAS '95 (1995).

  • Social Information Filtering: Algorithms for Automating "Word of Mouth" , Upendra Shardanand and Pattie Maes, MIT Media-Lab, CHI-95. This paper describes a technique for making personalized recommendations from any type of database to a user based on similarities between the interest profile of that user and those of other users. In particular, we discuss the implementation of a networked system called Ringo, which makes personalized recommendations for music albums and artists.

Edited by Tim Finin & Yannis Labrou of UMBC ebiquity and the UMBC Computer Science and Electrical Engineering Department. Comments to agentweb@agents.umbc.edu. Hits in red Who points to it? shows inverse links. Built by bk2site.