Advertisement

Journal of Intelligent Information Systems

, Volume 9, Issue 3, pp 239–260 | Cite as

Intelligent Adaptive Information Agents

  • Keith S. Decker
  • Katia Sycara
Article

Abstract

Adaptation in open, multi-agent information gathering systems isimportant for several reasons. These reasons include the inability toaccurately predict future problem-solving workloads, future changes inexisting information requests, future failures and additions of agents anddata supply resources, and other future task environment characteristicchanges that require system reorganization. We have developed a multi-agentdistributed system infrastructure, RETSINA (REusable Task Structure-based Intelligent Network Agents) that handles adaptation in an open Internetenvironment. Adaptation occurs both at the individual agent level as well asat the overall agent organization level. The RETSINA system has three typesof agents. Interface agents interact with the userreceiving user specifications and delivering results. They acquire, model,and utilize user preferences to guide system coordination in support of theuser‘s tasks. Task agents help users perform tasks byformulating problem solving plans and carrying out these plans throughquerying and exchanging information with other software agents. Information agents provide intelligent access to a heterogeneouscollection of information sources. In this paper, we concentrate on theadaptive architecture of the information agents. We use as the domain ofapplication WARREN, a multi-agent financial portfolio management system thatwe have implemented within the RETSINA framework.

Multi-Agent Systems Intelligent Agents Distributed AI Agent Architectures Information Gathering 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Cohen, P.R. and H. J. Levesque. Intention=choice + commitment. In Proceedings of AAAI-87, pages 410–415, Seattle, WA., 1987. AAAI.Google Scholar
  2. Cohen, Paul, Michael Greenberg, David Hart, and Adele Howe. Trial by fire: Understanding the design requirements for agents in complex environments. AI Magazine, 10(3):33–48, Fall 1989. Also COINS-TR-89-61.Google Scholar
  3. Cohen, Philip R. and Hector J. Levesque. Intention is choice with commitment. Artificial Intelligence, 42(3):213–261, 1990.Google Scholar
  4. Cohen, P.R. and H.J. Levesque. Communicative actions for artificial agents. In Proceedings of the First International Conference on Multi-Agent Systems, pages 65–72, San Francisco, June 1995. AAAI Press.Google Scholar
  5. Collet, C., M.N. Huhns, and W. Shen. Resource integration using a large knowledge base in Carnot. Computer, pages 55–62, December 1991.Google Scholar
  6. Davis, R. and R. G. Smith. Negotiation as a metaphor for distributed problem solving. Artificial Intelligence, 20(1):63–109, January 1983.Google Scholar
  7. Decker, K.S., V.R. Lesser, M.V. Nagendra Prasad, and T. Wagner. MACRON: an architecture for multi-agent cooperative information gathering. In Proccedings of the CIKM-95Workshop on Intelligent Information Agents, Baltimore, MD, 1995.Google Scholar
  8. Decker, K.S., K. Sycara, and M. Williamson. Middle-agents for the internet. In Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, Nagoya, Japan, August 1997.Google Scholar
  9. Decker, K.S., M. Williamson, and K. Sycara. Modeling information agents: Advertisements, organizational roles, and dynamic behavior. In Proceedings of the AAAI-96 Workshop on Agent Modeling, 1996. AAAI Report WS-96-02.Google Scholar
  10. Decker, Keith S. Task environment centered simulation. In M. Prietula, K. Carley, and L. Gasser, editors, Simulating Organizations: Computational Models of Institutions and Groups. AAAI Press/MIT Press, 1997. Forthcoming.Google Scholar
  11. Decker, Keith S. and Victor R. Lesser. An approach to analyzing the need for meta-level communication. In Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, pages 360–366, Chambéry, France, August 1993.Google Scholar
  12. Decker, Keith S. and Victor R. Lesser. A one-shot dynamic coordination algorithm for distributed sensor networks. In Proceedings of the Eleventh National Conference on Artificial Intelligence, pages 210–216,Washington, July 1993.Google Scholar
  13. Decker, Keith S. and Victor R. Lesser. Quantitative modeling of complex computational task environments. In Proceedings of the Eleventh National Conference on Artificial Intelligence, pages 217–224, Washington, July 1993.Google Scholar
  14. Decker, Keith S. and Victor R. Lesser. Designing a family of coordination algorithms. In Proceedings of the First International Conference on Multi-Agent Systems, pages 73–80, San Francisco, June 1995. AAAI Press. Longer version available as UMass CS-TR 94–14.Google Scholar
  15. Draper, D., S. Hanks, and D. Weld. Probabilistic planning with information gathering and contingent execution. In Proc. 2nd Intl. Conf. on A.I. Planning Systems, June 1994.Google Scholar
  16. Etzioni, O., S. Hanks, D. Weld, D. Draper, N. Lesh, and M. Williamson. An Approach to Planning with Incomplete Information. In Proc. 3rd Int. Conf. on Principles of Knowledge Representation and Reasoning, San Francisco, CA, October 1992. Morgan Kaufmann. Available via FTP from pub/ai/ at ftp.cs.washington.edu.Google Scholar
  17. Etzioni, Oren, Neal Lesh, and Richard Segal. Building softbots for unix (preliminary report). Technical Report softbots-tr.ps, University of Washington, 1992.Google Scholar
  18. Etzioni, Oren and Daniel Weld. A softbot-based interface to the internet. Communications of the ACM, 37(7), July 1994.Google Scholar
  19. Finin, T., R. Fritzson, D. McKay, and R. McEntire. KQML as an agent communication language. In Proceedings of the Third International Conference on Information and Knowledge Management CIKM’94. ACM Press, November 1994.Google Scholar
  20. Garvey, Alan, Marty Humphrey, and Victor Lesser. Task interdependencies in design-to-time real-time scheduling. In Proceedings of the Eleventh National Conference on Artificial Intelligence, pages 580–585,Washington, July 1993.Google Scholar
  21. Garvey, Alan and Victor Lesser. Representing and scheduling satisficing tasks. In Swaminathan Natarajan, editor, Imprecise and Approximate Computation, pages 23–34. Kluwer Academic Publishers, Norwell, MA, 1995.Google Scholar
  22. Genesereth, M.R. and S.P. Ketchpel. Software agents. Communications of the ACM, 37(7):48–53,147, 1994.Google Scholar
  23. Goodwin, R. Using loops in decision-theoretic refinement planners. In Proc. 3rd Intl. Conf. on A.I. Planning Systems, 1996.Google Scholar
  24. Gruber, T.R. Toward principles for the design of ontologies used for knowledge sharing. Technical Report KSL-93-4, Knowledge Systems Laboratory, Stanford University, 1993.Google Scholar
  25. Jennings, N.R. Commitments and conventions: The foundation of coordination in multi-agent systems. The Knowledge Engineering Review, 8(3):223–250, 1993.Google Scholar
  26. Kim, W. and J. Seo. Classifying schematic and data heterogeneity in multidatabase systems. Computer, pages 12–18, December 1991.Google Scholar
  27. Knoblock, C. Generating parallel execution plans with a partial-order planner. In Proc. 2nd Intl. Conf. on A.I. Planning Systems, pages 98–103, June 1994.Google Scholar
  28. Knoblock, C.A., Y. Arens, and C. Hsu. Cooperating agents for information retrieval. In Proc. 2nd Intl. Conf. on Cooperative Information Systems. Univ. of Toronto Press, 1994.Google Scholar
  29. Kuokka, D. and L. Harada. On using KQML for matchmaking. In Proceedings of the First International Conference on Multi-Agent Systems, pages 239–245, San Francisco, June 1995. AAAI Press.Google Scholar
  30. Labrou, Y. and T. Finin. A semantics approach for KQML. In Proceedings of the Third International Conference on Information and Knowledge Management CIKM’94. ACM Press, November 1994.Google Scholar
  31. Labrou, Y. and T. Finin. A proposal for a new kqml specification. CSEE Technical Report TR CS–97–03, University of Maryland Baltimore County, August 1997.Google Scholar
  32. Lang, Kan. Newsweeder: Learning to filter netnews. In Proceedings of Machine Learning Conference, 1995.Google Scholar
  33. Lawrence, Paul and Jay Lorsch. Organization and Environment. Harvard University Press, Cambridge, MA, 1967.Google Scholar
  34. Lin, S. and T. Dean. Generating optimal policies for markov decision processes formulated as plans with conditional branches and loops. In Proc. 2nd European Planning Workshop, 1995.Google Scholar
  35. Maes, Pattie. Agents that reduce work and information overload. Communications of the ACM, 37(7), July 1994.Google Scholar
  36. Mitchell, Tom, Rich Caruana, Dayne Freitag, John McDermott, and David Zabowski. Experience with a learning personal assistant. Communications of the ACM, 37(7), July 1994.Google Scholar
  37. Moore, R. A Formal Theory of Knowledge and Action. In J. Hobbs and R. Moore, editors, Formal Theories of the Commonsense World. Ablex, Norwood, NJ, 1985.Google Scholar
  38. Musliner, D.J. Scheduling issues arising from automated real-time system design. Technical Report CS-TR-3364, UMIACS-TR-94-118, Department of Computer Science, University of Maryland, 1994.Google Scholar
  39. Ngo, L. and P. Haddawy. Representing iterative loops for decision-theoretic planning. In Working Notes of the AAAI Spring Symposium on Extending Theories of Action, 1995.Google Scholar
  40. Oates, Tim, M. V. Nagendra Prasad, Victor R. Lesser, and Keith S. Decker. A distributed problem solving approach to cooperative information gathering. In AAAI Spring Symposium on Information Gathering in Distributed Environments, Stanford University, March 1995.Google Scholar
  41. Peot, M. and D. Smith. Conditional Nonlinear Planning. In Proc. 1st Intl. Conf. on A.I. Planning Systems, pages 189–197, June 1992.Google Scholar
  42. Rao, A.S. and M.P. Georgeff. BDI agents: From theory to practice. In Proceedings of the First International Conference on Multi-Agent Systems, pages 312–319, San Francisco, June 1995. AAAI Press.Google Scholar
  43. Scott, W. Richard. Organizations: Rational, Natural, and Open Systems. Prentice-Hall, Inc., Englewood Cliffs, NJ, 1987.Google Scholar
  44. Searle, J.R. Speech Acts: An Essay in the Philosophy of Language. Cambridge University Press, Cambridge, 1969.Google Scholar
  45. Simmons, R. Structured control for autonomous robots. IEEE Trans. on Robotics and Automation, 10(1), February 1994.Google Scholar
  46. Smith, D. and M. Williamson. Representation and evaluation of plans with loops. In Working Notes of the AAAI Spring Symposium on Extended Theories of Action: Formal Theory and Practical Applications, Stanford, CA, 1995.Google Scholar
  47. Smith, I.A. and P.R. Cohen. Toward a semantics for an agent communication language based on speech acts. In Proceedings of the Thirteenth National Conference on Artificial Intelligence, pages 24–31, August 1996.Google Scholar
  48. Sycara, K., K. S. Decker, A. Pannu, M. Williamson, and D. Zeng. Distributed intelligent agents. IEEE Expert, 11(6):36–46, December 1996.Google Scholar
  49. Sycara, Katia and Dajun Zeng. Towards an intelligent electronic secretary. In Proceedings of the CIKM-94 (International Conference on Information and Knowledge Management) Workshop on Intelligent Information Agents, National Institute of Standards and Technology, Gaithersburg, Maryland, December 1994.Google Scholar
  50. Wagner, T., A. Garvey, and V. Lesser. Complex goal criteria and its application in design-to-criteria scheduling. In Proceedings of the Fourteenth National Conference on Artificial Intelligence, Providence, July 1997.Google Scholar
  51. Wellman, Michael. A market-oriented programming environment and its application to distributed multicommodity flow problems. Journal of Artificial Intelligence Research, 1:1–23, 1993.Google Scholar
  52. Wiederhold, G., P. Wegner, and S. Cefi. Toward megaprogramming. Communications of the ACM, 33(11):89–99, 1992.Google Scholar
  53. Williamson, M., K. S. Decker, and K. Sycara. Executing decision-theoretic plans in multi-agent environments. In AAAI Fall Symposium on Plan Execution, November 1996. AAAI Report FS-96-01.Google Scholar
  54. Williamson, M., K. S. Decker, and K. Sycara. Unified information and control flow in hierarchical task networks. In Proceedings of the AAAI-96 workshop on Theories of Planning, Action, and Control, 1996.Google Scholar
  55. Wooldridge, M. and N.R. Jennings. Intelligent agents: Theory and practice. The Knowledge Engineering Review, 10(2):115–152, 1995.Google Scholar

Copyright information

© Kluwer Academic Publishers 1997

Authors and Affiliations

  • Keith S. Decker
    • 1
  • Katia Sycara
    • 2
  1. 1.Department of Computer and Information SciencesUniversity of DelawareNewark
  2. 2.The Robotics Institute, Carnegie-Mellon UniversityPittsburgh

Personalised recommendations