Back

A Roadmap of Agent Research and Development

NICHOLAS R. JENNINGSKATIA SYCARAMICHAEL WOOLDRIDGE

article2004AAMAS2,380 citations

Establishes foundational definitions of agency and multi-agent interaction while outlining core principles, historical context, and open engineering challenges in autonomous system design.

Listen

Modern software engineering faces escalating complexity as computing systems expand into highly decentralized, dynamic, and open settings such as the Internet and automated industrial networks. Traditional programming models struggle to manage the unpredictable interactions, time constraints, and multi-party coordination required in these domains. The article provides a structured roadmap of autonomous agents and multi-agent systems, organizing key concepts across individual architectures, group interactions, and practical applications to establish agent-based computing as a coherent discipline.

To conduct this evaluation, the authors synthesize foundational theories and engineering practices spanning several decades across artificial intelligence, object-oriented systems, human-computer interfaces, and economics. They analyze historical single-agent architectures—tracing the transition from rigid symbolic planning to reactive systems and multi-layered hybrid models—and examine group dynamics across cooperative teamwork frameworks, automated negotiation protocols, and open-network directory services.

First, an effective agent requires situatedness, autonomy, and flexible behavior encompassing responsiveness, pro-activeness, and social capability, differentiating it from traditional passive objects. Second, hybrid architectures successfully balance real-time reactive behaviors with high-level deliberative goal planning, resolving the computational bottlenecks of early symbolic systems. Third, cooperative multi-agent coordination requires explicit representations of shared intentions and dynamic control to avoid system deadlocks. Fourth, in self-interested networks, market mechanisms and structured negotiation protocols can align local agent decisions with global system stability, though unbalanced learning among agents can degrade overall system performance. Finally, practical deployments across manufacturing, telecommunications, air-traffic management, and electronic commerce demonstrate that agent abstractions provide immediate software engineering value in complex domains.

These findings indicate that treating software components as autonomous, negotiating entities significantly reduces development overhead for distributed and legacy system integration. However, realizing widespread adoption depends on overcoming major engineering hurdles. Development teams should not build custom infrastructure from scratch; instead, industry efforts must focus on standardizing agent communication languages, shared knowledge definitions, and production-grade software development toolkits. Additionally, organizations deploying these systems must carefully calibrate operational autonomy to establish user trust and ensure safe, predictable human-agent collaboration.

Carnegie Mellon UniversityQueen Mary University of Londonagent basedagent systemsautonomous agentsAgentsAgentArti Cial Intelligence
JENNINGS et al (2004).pdf
Cover for A Roadmap of Agent Research and Development

Abstract

This paper provides an overview of research and development activities in the field of autonomous agents and multi-agent systems. It aims to identify key concepts and applications, and to indicate how they relate to one-another. Some historical context to the field of agent-based computing is given, and contemporary research directions are presented. Finally, a range of open issues and future challenges are highlighted.

Topics

agent basedagent systemsautonomous agentsmulti-agentsoftware agents

Keywords

AgentsAgentArti Cial IntelligenceResearchInformationMulti-AgentControlPagesApplicationsMulti-Agent Systems

Table of Contents

  • 2. Autonomous Agents
  • 2.1. History
  • 2.2. Issues and Future Directions
  • 3. Multi-Agent Systems
  • 3.1. History
  • 3.1.3. Some Early Applications
  • 3.2. Cooperative Multi-Agent Interactions
  • 3.3. Self-Interested Multi Agent Interactions
  • 3.4. Issues and Future Directions
  • 4. Applications
  • 4.1. Key Domains and Exemplar Systems
  • 4.2. Future Directions
  • 5. Concluding Remarks
  • Notes
  • References

Knowls

  1. Knowl 1 — Definition and Core Properties of an Autonomous Agent

    definition

    An agent is defined as a computer system situated within an environment that is capable of flexible autonomous action in order to meet its design objectives. This definition rests on three primary concepts:

    1. Situatedness: The system receives sensory input from its environment (e.g., the physical world or the Internet) and performs actions that can modify that environment.
    2. Autonomy: The system acts without the direct intervention of humans or other systems, retaining control over its own internal state and actions.
    3. Flexibility: The system exhibits three simultaneous behavioral characteristics:
      • Responsiveness: Perceives changes in the environment and responds in a timely manner.
      • Pro-activeness: Takes the initiative and exhibits opportunistic, goal-directed behavior rather than purely reacting to external stimuli.
      • Social ability: Interacts appropriately with other artificial agents and humans to fulfill tasks and assist other entities.

  2. Knowl 2 — Architectural Distinctions Between Agents and Objects

    definition

    While both agents and objects encapsulate internal state and communicate via message passing, they differ fundamentally across three dimensions:

    1. Degree of Autonomy (Locus of Control): In the standard object-oriented paradigm, an object controls its internal state through encapsulation (private variables), but lacks autonomy over its behavior: invoking a public method on an object forces its execution by the caller. In contrast, an agent controls both its internal state and its behavior: when an agent receives a request to perform an action, the locus of control remains with the receiver, which evaluates whether executing the requested action is consistent with its own goals and interests.
    2. Flexibility and Integrated Behavior: The standard object model provides no abstractions for integrating reactive, pro-active, and social behaviors within an entity.
    3. Thread of Control: A standard object-oriented system typically operates with a single thread of control (or passive concurrent objects), whereas agents inherently possess independent threads of control.

  3. Knowl 3 — Definition and Defining Characteristics of Multi-Agent Systems

    definition

    A Multi-Agent System (MAS) is a loosely coupled network of problem solvers (autonomous agents) that interact to address problems beyond the individual capabilities or knowledge of any single problem solver.

    A MAS is defined by four core operational characteristics:

    1. Incomplete Information and Limited Viewpoints: No single agent possesses complete information or full capability to solve the overall problem, restricting each agent to a localized perspective.
    2. Absence of Global System Control: System behavior is decentralized; no central authority controls global problem-solving.
    3. Decentralized Data: Data and knowledge are distributed across different nodes.
    4. Asynchronous Computation: Agents execute actions and process information asynchronously.

  4. Knowl 4 — The Calculative Rationality Assumption in Deliberative Planning

    assumption

    The calculative rationality assumption in classical first-principles planning posits that an agent decision-making function ff is rational if the action a=f(s0)a = f(s_0) produced at time t1t_1 is optimal with respect to the environmental observation s0s_0 recorded at the initial deliberation time t0t_0.

    In dynamic, time-constrained environments, this assumption breaks down. First-principles planning involves searching an action space whose complexity grows exponentially with task complexity. Because the decision computation requires non-negligible duration (t1−t0>0t_1 - t_0 > 0), the optimal action computed for state s0s_0 may no longer be valid or useful by the time it is executed at t1t_1, necessitating reactive or hybrid agent architectures.

  5. Knowl 5 — Hybrid Layered Agent Architectures: Horizontal vs. Vertical Layering

    model/method

    Hybrid agent architectures combine reactive and deliberative behaviors by structuring the agent's control into hierarchical software layers. A typical system contains three levels of abstraction:

    1. A reactive layer at the base that maps raw sensor data to rapid reflexive actions.
    2. A middle layer operating on symbolic knowledge-level representations of the environment.
    3. A social layer at the top that reasons about external agents, their beliefs, and their goals.

    These layers are connected via one of two structural arrangements:

    • Horizontal Layering: All layers simultaneously receive raw perceptual input and generate candidate action outputs. A centralized control or rule-based mediation subsystem arbitrates among competing layer outputs to select the global action.
    • Vertical Layering: Perceptual input enters one layer and is filtered sequentially up or down the hierarchy, with only a single terminal layer issuing actions to the effectors, avoiding external mediation conflicts.

  6. Knowl 6 — Belief-Desire-Intention (BDI) Practical Reasoning Model

    model/method

    The Belief-Desire-Intention (BDI) model is an agent architecture based on philosophical theories of human practical reasoning. An agent's mental state is composed of three mentalistic attitudes:

    1. Beliefs: Information the agent possesses regarding the state of its operating environment.
    2. Desires: Potential options or possible future states of affairs available for the agent to achieve.
    3. Intentions: A subset of desires that the agent has explicitly selected, committed computational and physical resources to, and organized into executable plans.

    The practical reasoning cycle consists of iteratively updating beliefs from perceptual input, generating available options (desires), filtering desires against existing commitments to adopt new intentions, and executing actions derived from the active intentions.

  7. Knowl 7 — Teamwork Frameworks: Joint Intentions and SharedPlans

    model/method

    To coordinate multi-agent teams in dynamic and uncertain environments, cooperative agent systems employ explicit teamwork models rather than individual planning heuristics:

    • Joint Intentions Model: A team jointly intends a collective action if all members are jointly committed to completing it while mutually believing they are doing so. A joint commitment is formalized as a joint persistent goal. Establishing a joint commitment requires explicit synchronization through speech acts (request and confirmation protocols), ensuring that all members consent before the joint goal is established.
    • SharedPlans Model: Team coordination is formulated around the mental attitude of intending that an action be performed. Axioms in this model specify obligations for an agent to perform actions or communicate information that directly facilitates or enables teammates to execute their assigned tasks.

  8. Knowl 8 — Characterization of Multi-Agent Negotiation

    definition

    In multi-agent systems composed of self-interested entities, negotiation is defined as an iterative decentralized interaction process for conflict resolution and coordination. Realistic multi-agent negotiation is characterized by five necessary conditions:

    1. Decentralized Conflict Resolution: A disparity in agent plans, goals, or resource allocations must be resolved without a centralized coordinator.
    2. Self-Interested Agents: Each agent seeks to optimize its own utility rather than a shared global objective.
    3. Bounded Rationality: Agents possess finite computational resources and cannot perform unbounded optimization.
    4. Incomplete and Private Information: Agent utility functions, reservation values, and preferences are private and not common knowledge.
    5. Iterative Proposal Exchange: Agents interact by exchanging proposals and counter-proposals across single or multiple negotiation issues under temporal constraints.

  9. Knowl 9 — Middle Agent Taxonomy in Open Multi-Agent Systems

    model/method

    In open environments where agents enter, leave, and fail unpredictably, middle agents mediate discovery and interoperability. Agents advertise their service capabilities to middle agents, which are categorized into three operational classes:

    1. Matchmakers (Yellow Page Agents): Store advertisements of agent capabilities. When an agent submits a service request, the matchmaker returns a list of matching candidate agents, allowing the requester to contact them directly.
    2. Blackboard Agents: Store submitted problem requests. Service-providing agents monitor the blackboard to find and fulfill requests they are capable of handling.
    3. Brokers: Accept service requests from clients, process and route them directly to capable service providers, and return the resulting outputs back to the original requesters, acting as complete intermediaries.

  10. Knowl 10 — Primary Technical and Social Impediments to Multi-Agent System Adoption

    limitation

    The widespread deployment of multi-agent systems in mainstream software engineering faces three major challenges:

    1. Lack of Systematic Engineering Methodologies: Absence of standardized methodologies to decompose problem domains into agent abstractions, structure individual agent internals, and specify interaction regimes, forcing developers to rely on ad hoc adaptations of object-oriented techniques.
    2. Lack of Industrial-Strength MAS Toolkits: Absence of mature development environments that natively support agent-level abstractions (such as mental state manipulation, agent communication protocols, and multi-agent visualization/debugging), requiring developers to build low-level infrastructure repeatedly.
    3. The Delegation and User Trust Barrier: Delegating autonomous decision-making to software requires users to establish trust over time. Agents must balance autonomy with authority by knowing when to request guidance versus acting autonomously without distracting the user.

Coverage note — Specific historical descriptions of third-party legacy software systems (e.g., ARCHON, OASIS, YAMS, WARRENS, PERSUADER) were omitted as standalone knowls, as they represent specific survey illustrations rather than the core conceptual and architectural framework contributed by the roadmap.

References

  1. 1.M. R. Adler, A. B. Davis, R. Weihmayer, and R. W. Worrest. Conflict resolution strategies for nonhierarchical distributed agents. In L. Gasser and M. Huhns, editors, Distributed Artificial Intelligence Volume II, pages 139–162. Pitman Publishing: London and Morgan Kaufmann: San Mateo, CA, 1989.
  2. 2.G. Agha. ACTORS: A Model of Concurrent Computation in Distributed Systems. The MIT Press: Cambridge, MA, 1986.
  3. 3.G. Agha and C. Hewitt. Concurrent programming using actors. In Y. Yonezawa and M. Tokoro, editors, Object-Oriented Concurrent Programming. MIT Press, 1988.
  4. 4.G. Agha, P. Wegner, and A. Yonezawa, editors. Research Directions in Concurrent Object-Oriented Programming. The MIT Press: Cambridge, MA, 1993.
  5. 5.J. F. Allen, J. Hendler, and A. Tate, editors. Readings in Planning. Morgan Kaufmann Publishers: San Mateo, CA, 1990.
  6. 6.J. Bates. The role of emotion in believable agents. Communications of the ACM, 37(7):122–125, July 1994.
  7. 7.K. Binmore. Fun and Games: A Text on Game Theory. D. C. Heath and Company: Lexington, MA, 1992.
  8. 8.R. P. Bonasso, D. Kortenkamp, D. P. Miller, and M. Slack. Experiences with an architecture for intelligent, reactive agents. In M. Wooldridge, J. P. Müller, and M. Tambe, editors, Intelligent Agents II (LNAI Volume 1037), pages 187–202. Springer-Verlag: Berlin, Germany, 1996.
  9. 9.A. H. Bond and L. Gasser, editors. Readings in Distributed Artificial Intelligence. Morgan Kaufmann Publishers: San Mateo, CA, 1988.
  10. 10.G. Booch. Object-Oriented Analysis and Design (second edition). Addison-Wesley: Reading, MA, 1994.
  11. 11.J. Bradshaw, editor. Software Agents. The MIT Press: Cambridge, MA, 1997.
  12. 12.M. E. Bratman. Intentions, Plans, and Practical Reason. Harvard University Press: Cambridge, MA, 1987.
  13. 13.M. E. Bratman. Planning and the stability of intentions. Minds and Machines, 2:1–16, 1992.
  14. 14.M. E. Bratman, D. J. Israel, and M. E. Pollack. Plans and resource-bounded practical reasoning. Computational Intelligence, 4:349–355, 1988.
  15. 15.R. A. Brooks. A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, 2(1):14–23, 1986.
  16. 16.R. A. Brooks. Intelligence without reason. In Proceedings of the Twelfth International Joint Conference on Artificial Intelligence (IJCAI-91), pages 569–595, Sydney, Australia, 1991.
  17. 17.R. A. Brooks. Intelligence without representation. Artificial Intelligence, 47:139–159, 1991.
  18. 18.B. Burmeister, A. Haddadi, and G. Matylis. Applications of multi-agent systems in traffic and transportation. IEE Transactions on Software Engineering, 144(1):51–60, February 1997.
  19. 19.M. Busuoic and D. Griffiths. Cooperating intelligent agents for service management in communications networks. In S. M. Deen, editor, Proceedings of the 1993 Workshop on Cooperating Knowledge Based Systems (CKBS-93), pages 213–226. DAKE Centre, University of Keele, UK, 1994.
  20. 20.A. Caglayan, M. Snorrason, J. Mazzu J. Jacoby, R. Jones, and K. Kumar. Open sesame – a learning agent engine. Applied Artificial Intelligence, 11(5):393–412, 1997.
  21. 21.S. Cammarata, D. McArthur, and R. Steeb. Strategies of cooperation in distributed problem solving. In Proceedings of the Eighth International Joint Conference on Artificial Intelligence (IJCAI-83), Karlsruhe, Federal Republic of Germany, 1983.
  22. 22.B. Chaib-draa. Industrial applications of distributed ai. Communications of the ACM, 38(11):47–53, 1995.
  23. 23.D. Chapman. Planning for conjunctive goals. Artificial Intelligence, 32:333–378, 1987.
  24. 24.A. Chavez and P. Maes. Kasbah: An agent marketplace for buying and selling goods. In Proceedings of the First International Conference on the Practical Application of Intelligent Agents and Multi-Agent Technology (PAAM-96), pages 75–90, London, UK, 1996.
  25. 25.Liren Chen and Katia Sycara. Webmate : A personal agent for browsing and searching. In Proceedings of the Second International Conference on Autonomous Agents (Agents 98), Minneapolis/St Paul, MN, May 1998.
  26. 26.K. T. Chung and C. H. Wu. Dynamic scheduling with intelligent agents. Metra Application Note 105, Metra, Palo Alto, CA, 1997.
  27. 27.S. H. Clearwater, R. Costanza, M. Dixon, and B. Schroeder. Saving energy using market-based control. In S. H. Clearwater, editor, Market Based Control, pages 253–273. World Scientific: Singapore, 1996.
  28. 28.P. R. Cohen and H. J. Levesque. Teamwork. Nous, 25(4):487–512, 1991.
  29. 29.J. M. Corera, I. Laresgoiti, and N. R.Jennings. Using archon, part 2: Electricity transportation management. IEEE Expert, 11(6):71–79, 1996.
  30. 30.D. D. Corkill and V. R. Lesser. The use of meta-level control for coordination in a distributed problem solving network. In Proceedings of the Eighth International Joint Conference on Artificial Intelligence (IJCAI-83), pages 748–756, Karlsruhe, Germany, 1983.
  31. 31.M. R. Cutosky, R. E. Fikes R. S. Engelmore, M. R. Genesereth, W. S. Mark T. Gruber, J. M. Tenenbaum, and J. C. Weber. PACT: An experiment in integrating concurrent engineering systems. IEEE Transactions on Computers, 26(1):28–37, 1993.
  32. 32.T. P. Darr and W. P. Birmingham. An attribute-space representation and algorithm for concurrent engineering. AI EDAM, 10(1):21–35, 1996.
  33. 33.Davis, R. and R. G. Smith. Negotiation as a metaphor for distributed problem solving. Artificial Intelligence, 20:63–100, 1983.
  34. 34.K. Decker and V. Lesser. Designing a family of coordination algorithms. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), pages 73–80, San Francisco, CA, June 1995.
  35. 35.K. Decker, A. Pannu, K. Sycara, and M. Williamson. Designing behaviors for information agents. In Proceedings of the First International Conference on Autonomous Agents (Agents-97), pages 404–412, Marina del Rey, CA, February 1997.
  36. 36.K. Decker, K. Sycara, and M. Williamson. Middle-agents for the internet. In Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence (IJCAI-97), Nagoya, Japan, 1997.
  37. 37.R. Doorenbos, O. Etzioni, and D. Weld. A scaleable comparison-shopping agent for the world wide web. In Proceedings of the First International Conference on Autonomous Agents (Agents 97), pages 39–48, Marina del Rey, CA, 1997.
  38. 38.E. H. Durfee. Coordination of Distributed Problem Solvers. Kluwer Academic Publishers: Boston, MA, 1988.
  39. 39.E. H. Durfee and V. Lesser. Negotiating task decomposition and allocation using partial global planning. In L. Gasser and M. Huhns, editors, Distributed Artificial Intelligence Volume II, pages 229–244. Pitman Publishing: London and Morgan Kaufmann: San Mateo, CA, 1989.
  40. 40.R. Engelmore and T. Morgan, editors. Blackboard Systems. Addison-Wesley: Reading, MA, 1988.
  41. 41.B. Esfandiari, G. Deflandre, and J. Quinqueton. An interface agent for network supervision. In Proceedings of the ECAI-96 Workshop on Intelligent Agents for Telecom Applications, Budapest, Hungary, 1996.
  42. 42.O. Etzioni. Moving up the information food chain: Deploying softbots on the world-wide web. In Proceedings of the Thirteenth National Conference on Artificial Intelligence (AAAI-96), Portland, OR, 1996.
  43. 43.I. A. Ferguson. TouringMachines: An Architecture for Dynamic, Rational, Mobile Agents. PhD thesis, Clare Hall, University of Cambridge, UK, November 1992. (Also available as Technical Report No. 273, University of Cambridge Computer Laboratory).
  44. 44.I. A. Ferguson. Integrated control and coordinated behaviour: A case for agent models. In M. Wooldridge and N. R. Jennings, editors, Intelligent Agents: Theories, Architectures, and Languages (LNAI Volume 890), pages 203–218. Springer-Verlag: Berlin, Germany, January 1995.
  45. 45.R. E. Fikes and N. Nilsson. STRIPS: A new approach to the application of theorem proving to problem solving. Artificial Intelligence, 5(2):189–208, 1971.
  46. 46.K. Fischer, J. P. Müller, and M. Pischel. Cooperative transportation scheduling: An application domain for dai. Applied Artificial Intelligence, 10(1):1–34, 1996.
  47. 47.M. Fisher. Representing and executing agent-based systems. In M. Wooldridge and N. R. Jennings, editors, Intelligent Agents: Theories, Architectures, and Languages (LNAI Volume 890), pages 307–323. Springer-Verlag: Berlin, Germany, January 1995.
  48. 48.L. N. Foner. Entertaining agents: A sociological case study. In Proceedings of the First International Conference on Autonomous Agents (Agents 97), pages 122–129, Marina del Rey, CA, 1997.
  49. 49.The Foundation for Intelligent Physical Agents. See http://drogo.cselt.stet.it/fipa/.
  50. 50.K. Fordyce and G. G. Sullivan. Logistics management system: Integrating decision technologies for dispatch scheduling in semi-conductor manufacturing. In M. Zweben and M. S. Fox, editors, Intelligent Scheduling, pages 473–516. Morgan Kaufmann Publishers: San Mateo, CA, 1994.
  51. 51.M. S. Fox, J. F. Chionglo, and M. Barbuceanu. The integrated supply chain management system. Technical report, Department of Industrial Engineering, University of Toronto, 1993.
  52. 52.S. Franklin and A. Graesser. Is it an agent, or just a program? In J. P. Müller, M. Wooldridge, and N. R. Jennings, editors, Intelligent Agents III (LNAI Volume 1193), pages 21–36. Springer-Verlag: Berlin, Germany, 1997.
  53. 53.F. J. Garijo and D. Hoffmann. A multi-agent architecture for operation and maintenance of telecommunications networks. In Proceedings of the Twelfth International Conference on AI, Expert Systems and Natural Language, pages 427–436, Avignon, France, 1992.
  54. 54.L. Gasser. Social conceptions of knowledge and action. Artificial Intelligence, 43(1), 1991.
  55. 55.M. P. Georgeff. Communication and interaction in multi-agent planning. In Proceedings of the Third National Conference on Artificial Intelligence (AAAI-83), Washington, D.C., 1983.
  56. 56.M. P. Georgeff. Distributed multi-agent reasoning systems (dmars). Technical report, Australian AI Institute, Level 6, 171 La Trobe Street, Melbourne, Australia, 1994.
  57. 57.M. P. Georgeff and A. L. Lansky. Reactive reasoning and planning. In Proceedings of the Sixth National Conference on Artificial Intelligence (AAAI-87), pages 677–682, Seattle, WA, 1987.
  58. 58.S. Grand and D. Cliff. Creatures: Entertainment software agents with artificial life. Autonomous Agents and Multi-Agent Systems, 1(2), 1998.
  59. 59.N. D. Griffeth and H. Velthuijsen. The negotiating agents approach to run-time feature interaction resolution. In L. G. Bouma and H. Velthuijsen, editors, Feature Interactions in Telecommunications Systems, pages 217–235. IOS Press, 1994.
  60. 60.Barbara Grosz and Sarit Kraus. Collaborative plans for complex group actions. Artificial Intelligence, 86(2):269–3571, 1996.
  61. 61.Barbara Grosz and Candace Sidner. Plans for discourse. In Phil Cohen, Jerry Morgan, and Martha Pollack, editors, Intentions in Communication, pages 417–444. MIT Press, Cambdrige, MA, 1990.
  62. 62.T. R. Gruber. A translation approach to portable ontologies. Knowledge Acquisition, 5(2):199–220, 1993.
  63. 63.G. Hardin. The tragedy of commons. Science, 162:1243, 1968.
  64. 64.B. Hayes-Roth. A blackboard architecture for control. Artificial Intelligence, 26, 1985.
  65. 65.B. Hayes-Roth. Agents on stage: Advancing the state of the art in AI. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence (IJCAI-95), pages 967–971, Montréal, Québec, Canada, August 1995.
  66. 66.B. Hayes-Roth and L. Brownston. Multiagent collaboration in directed improvisation. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), pages 148–154, San Francisco, CA, June 1995.
  67. 67.B. Hayes-Roth, M. Hewett, R. Washington, R. Hewett, and A. Seiver. Distributing intelligence within an individual. In L. Gasser and M. Huhns, editors, Distributed Artificial Intelligence Volume II, pages 385–412. Pitman Publishing: London and Morgan Kaufmann: San Mateo, CA, 1989.
  68. 68.C. Hewitt and J. Inman. Dai betwist and between: From intelligent agents to open systems science. IEEE Trans. SMC, 21(6):1409–1418, 1991.
  69. 69.Junling Hu and Michael P. Wellman. Self-fulfilling bias in multiagent learning. In Proceedings of the Second International Conference on Multi-Agent Systems (ICMAS-96), Kyoto, Japan, 1996.
  70. 70.J. Huang, N. R. Jennings, and J. Fox. An agent-based approach to health care management. Applied Artificial Intelligence, 9(4):401–420, 1995.
  71. 71.B. A. Huberman and S. H. Clearwater. A multiagent system for controlling building environments. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), pages 171–176, San Francisco, CA, June 1995.
  72. 72.B. A. Huberman and T. Hogg. The behavior of computational ecologies. In B. A. Huberman, editor, The Ecology of Computation. North-Holland, Amsterdam, 1988.
  73. 73.M. Huhns, U. Mukhopadhyay, and L. M. Stephens. DAI for document retrieval: The MINDS project. In M. Huhns, editor, Distributed Artificial Intelligence, pages 249–284. Pitman Publishing: London and Morgan Kaufmann: San Mateo, CA, 1987.
  74. 74.M. Huhns and M. P. Singh, editors. Readings in Agents. Morgan Kaufmann Publishers: San Mateo, CA, 1998.
  75. 75.M. N. Huhns and M. P. Singh. Managing heterogeneous transaction workflows with cooperating agents. In N. R. Jennings and M. Wooldridge, editors, Agent Technology: Foundations, Applications and Markets. Springer-Verlag: Berlin, Germany, 1998.
  76. 76.F. F. Ingrand, M. P. Georgeff, and A. S. Rao. An architecture for real-time reasoning and system control. IEEE Expert, 7(6), 1992.
  77. 77.N. R. Jennings. Commitments and conventions: The foundation of coordination in multi-agent systems. The Knowledge Engineering Review, 8(3):223–250, 1993.
  78. 78.N. R. Jennings. Specification and implementation of a belief desire joint-intention architecture for collaborative problem solving. Journal of Intelligent and Cooperative Information Systems, 2(3):289–318, 1993.
  79. 79.N. R. Jennings. Controlling cooperative problem solving in industrial multi-agent systems using joint intentions. Artificial Intelligence, 74(2), 1995.
  80. 80.N. R. Jennings and J. R. Campos. Towards a social-level characterisation of socially responsible agents. IEE Transactions on Software Engineering, 144(1):11–25, February 1997.
  81. 81.N. R. Jennings, J. Corera, I. Laresgoiti, E. H. Mamdani, F. Perriolat, P. Skarek, and L. Z. Varga. Using ARCHON to develop real-world DAI applications for electricity transportation management and particle acceleration control. IEEE Expert, 11(6):60–88, December 1996.
  82. 82.N. R. Jennings, P. Faratin, M. J. Johnson, T. J. Norman, P. O’Brien, and M. E. Wiegand. Agent-based business process management. International Journal of Cooperative Information Systems, 5(2-3):105–130, 1996.
  83. 83.N. R. Jennings and M. Wooldridge. Applying agent technology. In N. R. Jennings and M. Wooldridge, editors, Agent Technology: Foundations, Applications, and Markets. Springer-Verlag: Berlin, Germany, 1998.
  84. 84.J. S.Jordan. The exponential covergence of bayesian learning in normal form games. Games and Economic Behavior, 4:202–217, 1992.
  85. 85.H. Kautz, B. Selman, and M. Shah. The hidden web. AI Magazine, 18(2):27–35, 1997.
  86. 86.S. Kraus, J. Wilkenfeld, and G. Zlotkin. Multiagent negotiation under time constraints. Artificial Intelligence, 75(2):297–345, 1995.
  87. 87.B. Krulwich. The BargainFinder agent: Comparison price shopping on the internet. In J. Williams, editor, Bots, and other Internet Beasties, pages 257–263. Macmillan Computer Publishing: Indianapolis, 1996.
  88. 88.D. R. Kuokka and L. P. Harada. Issues and extensions for information matchmaking protocols. International Journal of Cooperative Information Systems, 5(2-3):251–274, 1996.
  89. 89.Y. Lespérance, H. J. Levesque, F. Lin, D. Marcu, R. Reiter, and R. B. Scherl. Foundations of a logical approach to agent programming. In M. Wooldridge, J. P. Müller, and M. Tambe, editors, Intelligent Agents II (LNAI Volume 1037), pages 331–346. Springer-Verlag: Berlin, Germany, 1996.
  90. 90.V. R. Lesser, E. H. Durfee, and D. D. Corkill. Trends in cooperative distributed problem solving. IEEE Transaction on Knowledge and Data Engineering, 1(1):63–83, 1989.
  91. 91.V.R. Lesser. A retrospective view of fa/c distributed problem solving. IEEE Transactions on Systems, Man, and Cybernetics, Special Issue on Distributed Artificial Intelligence, 21(6):1347–1362, December 1991.
  92. 92.J. C. Lester and B. A. Stone. Increasing believability in animated pedagogical agents. In Proceedings of the First International Conference on Autonomous Agents (Agents 97), pages 16–21, Marina del Rey, CA, 1997.
  93. 93.H. J. Levesque, P. R. Cohen, and J. H. T. Nunes. On acting together. In Proceedings of the Eighth National Conference on Artificial Intelligence (AAAI-90), pages 94–99, Boston, MA, 1990.
  94. 94.H. Lieberman. Letizia: An agent that assists web browsing. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence (IJCAI-95), pages 924–929, Montréal, Québec, Canada, August 1995.
  95. 95.M. Ljunberg and A. Lucas. The OASIS air traffic management system. In Proceedings of the Second Pacific Rim International Conference on AI (PRICAI-92), Seoul, Korea, 1992.
  96. 96.Ovum Ltd. Intelligent agents: The next revolution in software, 1994.
  97. 97.P. Maes. Agents that reduce work and information overload. Communications of the ACM, 37(7):31–40, July 1994.
  98. 98.J. Mayfield, Y. Labrou, and T. Finin. Evaluating KQML as an agent communication language. In M. Wooldridge, J. P. Müller, and M. Tambe, editors, Intelligent Agents II (LNAI Volume 1037), pages 347–360. Springer-Verlag: Berlin, Germany, 1996.
  99. 99.F. G. McCabe and K. L. Clark. April — agent process interaction language. In M. Wooldridge and N. R. Jennings, editors, Intelligent Agents: Theories, Architectures, and Languages (LNAI Volume 890), pages 324–340. Springer-Verlag: Berlin, Germany, January 1995.
  100. 100.M. Merz, B. Lieberman, and W. Lamersdorf. Using mobile agents to support inter-organizational workflow management. Applied Artificial Intelligence, 11(6):551–572, 1997.
  101. 101.K. Mori, H. Torikoshi, K. Nakai, and T. Masuda. Computer control system for iron and steel plants. Hitachi Review, 37(4):251–258, 1988.
  102. 102.T. Mullen and M. P. Wellman. Some issues in the design of market-oriented agents. In M. Wooldridge, J. P. Müller, and M. Tambe, editors, Intelligent Agents II (LNAI 1037), pages 283–298. Springer-Verlag: Heidelberg, Germany, 1996.
  103. 103.J. P. Müller. The Design of Intelligent Agents (LNAI Volume 1177). Springer-Verlag: Berlin, Germany, 1997.
  104. 104.J. P. Müller and M. Pischel. Modelling interacting agents in dynamic environments. In Proceedings of the Eleventh European Conference on Artificial Intelligence (ECAI-94), pages 709–713, Amsterdam, The Netherlands, 1994.
  105. 105.Roger B. Myerson. Credible negotiation statements and coherent plans. Journal of economic theory, 48:264–303, 1989.
  106. 106.N. Negroponte. Being Digital. Hodder and Stoughton, 1995.
  107. 107.A. Newell. The knowledge level. Artificial Intelligence, 18(1):82–127, 1982.
  108. 108.A. Newell and H. A. Simon. GPS: A program that simulates human thought. In Lernende Automaten. R. Oldenbourg, KG, 1961.
  109. 109.Allen Newell. Unified Theories of Cognition. Harvard University Press, 1990.
  110. 110.Y. Nishibe, K. Kuwabara, T. Suda, and T. Ishida. Distributed channel allocation in atm networks. In Proceedings of the IEEE Globecom Conference, pages 12.2.1–12.2.7, Houston, TX., 1993.
  111. 111.G. M. P. O’Hare and N. R. Jennings, editors. Foundations of Distributed Artificial Intelligence. Wiley-Interscience: New York, 1996.
  112. 112.E. Oliveira, J. M. Fonseca, and A. Steiger-Garcao. MACIV: A DAI based resource management system. Applied Artificial Intelligence, 11(6):525–550, 1997.
  113. 113.L. Overgaard, H. G. Petersen, and J. W. Perram. Reactive motion planning: a multi-agent approach. Applied Artificial Intelligence, 10(1):35–52, 1996.
  114. 114.H. V. D. Parunak. Industrial and practical applications of dai. In G. Weiß, editor, Multi-Agent Systems. The MIT Press: Cambridge, MA, 1998.
  115. 115.H. V. D. Parunak, A. D. Baker, and S. J. Clark. The aaria agent architecture: An example of requirements-driven agent-based system design. In Proceedings of the First International Conference on Autonomous Agents (Agents 97), pages 482–483, Marina del Rey, CA, 1997.
  116. 116.H. V. D. Parunak, A. Ward, M. Fleischer, and J. Sauter. A marketplace of design agents for distributed concurrent set-based design. In Proceedings of the Fourth International Conference on Concurrent Engineering: Research and Applications, 1997.
  117. 117.F. Perriolat, P. Skarek, L. Z. Varga, and N. R. Jennings. Using archon: Particle accelerator control. IEEE Expert, 11(6):80–86, 1996.
  118. 118.M. E. Pollack and M. Ringuette. Introducing the Tileworld: Experimentally evaluating agent architectures. In Proceedings of the Eighth National Conference on Artificial Intelligence (AAAI-90), pages 183–189, Boston, MA, 1990.
  119. 119.A. S. Rao and M. P. Georgeff. Intelligent real-time network management. In Proceedings of the Tenth International Conference on AI, Expert Systems and Natural Language, Avignon, France, 1990.
  120. 120.A. S. Rao and M. P. Georgeff. Modeling rational agents within a BDI-architecture. In R. Fikes and E. Sandewall, editors, Proceedings of Knowledge Representation and Reasoning (KR&R-91), pages 473–484. Morgan Kaufmann Publishers: San Mateo, CA, April 1991.
  121. 121.A. S. Rao and M. P. Georgeff. An abstract architecture for rational agents. In C. Rich, W. Swartout, and B. Nebel, editors, Proceedings of Knowledge Representation and Reasoning (KR&R-92), pages 439–449, 1992.
  122. 122.C. Rich and C. Sidner. Collagen: When agents collaborate with people. In Proceedings of the International Conference on Autonomous Agents (Agents 97), Marina del Rey, CA, 1997.
  123. 123.J. S. Rosenschein. Rational Interaction: Cooperation Among Intelligent Agents. PhD thesis, Computer Science Department, Stanford University, Stanford, CA 94305, 1985.
  124. 124.J. S. Rosenschein and G. Zlotkin. Rules of Encounter: Designing Conventions for Automated Negotiation Among Computers. MIT Press, Boston, MA, 1994.
  125. 125.S. Russell and P. Norvig. Artificial Intelligence: A Modern Approach. Prentice-Hall, 1995.
  126. 126.S. Russell and D. Subramanian. Provably bounded-optimal agents. Journal of AI Research, 2:575–609, 1995.
  127. 127.T. Sandholm and V. Lesser. Issues in automated negotation and electronic commerce: extending the contract net protocol. In Proc. First Int. Conf. on Multiagent Systems (ICMAS-95), June 1995.
  128. 128.Tuomas Sandholm. An implementation of the contract net protocol based on marginal cost calculations. In Proceedings of the Eleventh National Conference on Artificial Intelligence, pages 256–262, Washington, July 1993.
  129. 129.R. Schoonderwoerd, O. Holland, and J. Bruten. Ant-like agents for load balancing in telecommunications networks. In Proceedings of the First International Conference on Autonomous Agents (Agents 97), pages 209–216, Marina del Rey, CA, 1997.
  130. 130.R. Schrooten and W. van de Velde. Software agent foundation for dynamic interactive electronic catalogues. Applied Artificial Intelligence, 11(5):459–482, 1997.
  131. 131.U. M. Schwuttke and A. G. Quan. Enhancing performance of cooperating agents in real-time diagnostic systems. In Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence (IJCAI-93), pages 332–337, Chambéry, France, 1993.
  132. 132.J. R. Searle. Speech Acts: An Essay in the Philosophy of Language. Cambridge University Press: Cambridge, England, 1969.
  133. 133.Y. Shoham. Agent-oriented programming. Artificial Intelligence, 60(1):51–92, 1993.
  134. 134.E. H. Shortliffe. Computer-Based Medical Consultations. Elsevier Science Publishers B.V.: Amsterdam, The Netherlands, 1976.
  135. 135.I. Smith and P. Cohen. Towards semantics for an agent communication language based on speech acts. In Proceedings of the Thirteenth National Conference on Artificial Intelligence (AAAI-96), Portland, OR, 1996.
  136. 136.F. Sprumont and J. P. Müller. Amacoia: A multi-agent system for designing flexible assembly lines. Applied Artificial Intelligence, 11(6):573–590, 1997.
  137. 137.L. Steels. Cooperation between distributed agents through self organization. In Y. Demazeau and J.-P. Müller, editors, Decentralized AI — Proceedings of the First European Workshop on Modelling Autonomous Agents in a Multi-Agent World (MAAMAW-89), pages 175–196. Elsevier Science Publishers B.V.: Amsterdam, The Netherlands, 1990.
  138. 138.P. Stone and M. Veloso. Multiagent systems: A survey from the machine learning perspective. IEEE Transactions on Knowledge and Data Engineering, Forthcoming, 1998.
  139. 139.K. Sycara. Negotiation planning: An AI approach. European Journal of Operational Research, 46:216–234, 1990.
  140. 140.K. P. Sycara. Resolving goal conflicts via negotiation. In Proceedings of the Seventh National Conference on Artificial Intelligence (AAAI-88), St. Paul, MN, 1988.
  141. 141.K. P. Sycara. Persuasive argumentation in negotiation. Theory and Decision, 28:203–242, 1990.
  142. 142.K. Takahashi, Y. Nishibe, I. Morihara, and F. Hattori. Intelligent pages: Collecting shop and service information with software agents. Applied Artificial Intelligence, 11(6):489–500, 1997.
  143. 143.M. Tambe. Recursive agent and agent group tracking in a real-time, dynamic environment. In Proceedings of the First International Conference on Multi-Agent Systems, pages 368–375, San Francisco, June 1995. AAAI Press.
  144. 144.Milind Tambe. Towards flexible teamwork. Journal of Artificial Intelligence Research, 7:83–124, 1997.
  145. 145.J. Thomas and K. Sycara. Stability and heterogeneity in multi agent systems. In Proceedings of the Third International Conference on Multi-Agent Systems (ICMAS-98), Paris, France, July, 1998.
  146. 146.R. Trappl and P. Petta. Creating Personalities for Synthetic Actors. Springer-Verlag: Berlin, Germany, 1997.
  147. 147.M. Tsvetovatyy, M. Gini, B. Mobasher, and Z. Wieckowski. MAGMA: An agent-based virtual marketplace for electronic commerce. Applied Artificial Intelligence, 11(6):501–524, 1997.
  148. 148.H. Van Dyke Parunak. Manufacturing experience with the contract net. In M. Huhns, editor, Distributed Artificial Intelligence, pages 285–310. Pitman Publishing: London and Morgan Kaufmann: San Mateo, CA, 1987.
  149. 149.Manuela Veloso, Peter Stone, Kwun Han, and Sorin Achim. Cmunited: A team of robotic soccer agents collaborating in an adversarial environment. In Proceedings of the The First International Workshop on RoboCup, Nagoya, Japan, August 1997. JCAI-97.
  150. 150.H. Wang and C. Wang. Intelligent agents in the nuclear industry. IEEE Computer, 30(11):28–34, 1997.
  151. 151.P. Wavish and M. Graham. A situated action approach to implementing characters in computer games. Applied Artificial Intelligence, 10(1):53–74, 1996.
  152. 152.R. Weihmayer, I. Ghaznavi, and P. Sheridan. A distributed architecture for cooperative management of strategic communications networks. In Proceedings of the IEE MILCOM’93 Conference, Boston, MA, 1993.
  153. 153.R. Weihmayer and H. Velthuijsen. Intelligent agents in telecommunications. In N. R. Jennings and M. J. Wooldridge, editors, Agent Technology: Foundations, Applications and Markets. Springer-Verlag: Berlin, Germany, 1998.
  154. 154.G. Weiß, editor. Multi-Agent Systems. The MIT Press: Cambridge, MA, 1998.
  155. 155.D. Wilkins. Practical Planning: Extending the Classical AI Planning Paradigm. Morgan Kaufmann Publishers: San Mateo, CA, 1988.
  156. 156.M. Wooldridge. Agent-based software engineering. IEE Transactions on Software Engineering, 144(1):26–37, February 1997.
  157. 157.M. Wooldridge, S. Bussmann, and M. Klosterberg. Production sequencing as negotiation. In Proceedings of the First International Conference on the Practical Application of Intelligent Agents and Multi-Agent Technology (PAAM-96), pages 709–726, London, UK, April 1996.
  158. 158.M. Wooldridge and N. R. Jennings. Intelligent agents: Theory and practice. The Knowledge Engineering Review, 10(2):115–152, 1995.
  159. 159.Dajun Zeng and Katia Sycara. Benefits of learning in negotiation. In Proceedings of AAAI-97, Providence, Rhode Island, U.S.A., 1997.
  160. 160.Dajun Zeng and Katia Sycara. Bayesian learning in negotiation. International Journal of Human-Computer Studies, 48, in press 1998.

Citation

MLA
Jennings, N. R., et al. “A Roadmap of Agent Research and Development”. Autonomous Agents and Multi-Agent Systems, vol. 1, no. 1, 1998, pp. 7–8, https://doi.org/10.1023/A:1010090405266.
APA
Jennings, N. R., Sycara, K., & Wooldridge, M. (1998). A Roadmap of Agent Research and Development. Autonomous Agents and Multi-Agent Systems, 1(1), 7–38. https://doi.org/10.1023/A:1010090405266
Chicago
Jennings, N. R., K. Sycara, and M. Wooldridge. 1998. “A Roadmap of Agent Research and Development”. Autonomous Agents and Multi-Agent Systems 1 (1): 7–38. https://doi.org/10.1023/A:1010090405266.
Harvard
Jennings, N.R., Sycara, K. and Wooldridge, M. (1998) “A Roadmap of Agent Research and Development”, Autonomous Agents and Multi-Agent Systems, 1(1), pp. 7–38. Available at: https://doi.org/10.1023/A:1010090405266.
Vancouver
1. Jennings NR, Sycara K, Wooldridge M (1998) A Roadmap of Agent Research and Development. Autonomous Agents and Multi-Agent Systems 1:7–38

BibTeX

@article{Jennings_1998, title={A Roadmap of Agent Research and Development}, volume={1}, ISSN={1573-7454}, url={http://dx.doi.org/10.1023/A:1010090405266}, DOI={10.1023/a:1010090405266}, number={1}, journal={Autonomous Agents and Multi-Agent Systems}, publisher={Springer Science and Business Media LLC}, author={Jennings, Nicholas R. and Sycara, Katia and Wooldridge, Michael}, year={1998}, month=Mar, pages={7–38} }
Metadata:Crossref

Access the Paper

This paper is available from its original source. Click below to access the PDF.

Open PDF