Coordination of multiple intelligent software agents

Katia Sycara, Dajun Zeng

Research output: Contribution to journalArticle

95 Citations (Scopus)

Abstract

We are investigating techniques for developing distributed and adaptive collections of information agents that coordinate to retrieve, filter and fuse information relevant to the user, task and situation, as well as anticipate user's information needs. In our system of agents, information gathering is seamlessly integrated with decision support. The task for which particular information is requested of the agents does not remain in the user's head but it is explicitly represented and supported through agent collaboration. In this paper we present the distributed system architecture, agent collaboration interactions, and a reusable set of software components for structuring agents. The system architecture has three types of agents: Interface agents interact with the user receiving user specifications and delivering results. They acquire, model, and utilize user preferences to guide system coordination in support of the user's tasks. Task agents help users perform tasks by formulating problem solving plans and carrying out these plans through querying and exchanging information with other software agents. Information agents provide intelligent access to a heterogeneous collection of information sources. We have implemented this system framework and are developing collaborating agents in diverse complex real world tasks, such as organizational decision making, investment counseling, health care and electronic commerce.

Original languageEnglish (US)
Pages (from-to)181-211
Number of pages31
JournalInternational Journal of Cooperative Information Systems
Volume5
Issue number2-3
StatePublished - 1996
Externally publishedYes

Fingerprint

Software agents
Intelligent agents
Electronic commerce
Electric fuses
Health care
Decision making
Specifications

Keywords

  • Coordination
  • Distributed AI
  • Information agent
  • Internet applications
  • Software agent

ASJC Scopus subject areas

  • Information Systems

Cite this

Coordination of multiple intelligent software agents. / Sycara, Katia; Zeng, Dajun.

In: International Journal of Cooperative Information Systems, Vol. 5, No. 2-3, 1996, p. 181-211.

Research output: Contribution to journalArticle

@article{ae737ac45b36485c8ec608d866441c98,
title = "Coordination of multiple intelligent software agents",
abstract = "We are investigating techniques for developing distributed and adaptive collections of information agents that coordinate to retrieve, filter and fuse information relevant to the user, task and situation, as well as anticipate user's information needs. In our system of agents, information gathering is seamlessly integrated with decision support. The task for which particular information is requested of the agents does not remain in the user's head but it is explicitly represented and supported through agent collaboration. In this paper we present the distributed system architecture, agent collaboration interactions, and a reusable set of software components for structuring agents. The system architecture has three types of agents: Interface agents interact with the user receiving user specifications and delivering results. They acquire, model, and utilize user preferences to guide system coordination in support of the user's tasks. Task agents help users perform tasks by formulating problem solving plans and carrying out these plans through querying and exchanging information with other software agents. Information agents provide intelligent access to a heterogeneous collection of information sources. We have implemented this system framework and are developing collaborating agents in diverse complex real world tasks, such as organizational decision making, investment counseling, health care and electronic commerce.",
keywords = "Coordination, Distributed AI, Information agent, Internet applications, Software agent",
author = "Katia Sycara and Dajun Zeng",
year = "1996",
language = "English (US)",
volume = "5",
pages = "181--211",
journal = "International Journal of Cooperative Information Systems",
issn = "0218-8430",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "2-3",

}

TY - JOUR

T1 - Coordination of multiple intelligent software agents

AU - Sycara, Katia

AU - Zeng, Dajun

PY - 1996

Y1 - 1996

N2 - We are investigating techniques for developing distributed and adaptive collections of information agents that coordinate to retrieve, filter and fuse information relevant to the user, task and situation, as well as anticipate user's information needs. In our system of agents, information gathering is seamlessly integrated with decision support. The task for which particular information is requested of the agents does not remain in the user's head but it is explicitly represented and supported through agent collaboration. In this paper we present the distributed system architecture, agent collaboration interactions, and a reusable set of software components for structuring agents. The system architecture has three types of agents: Interface agents interact with the user receiving user specifications and delivering results. They acquire, model, and utilize user preferences to guide system coordination in support of the user's tasks. Task agents help users perform tasks by formulating problem solving plans and carrying out these plans through querying and exchanging information with other software agents. Information agents provide intelligent access to a heterogeneous collection of information sources. We have implemented this system framework and are developing collaborating agents in diverse complex real world tasks, such as organizational decision making, investment counseling, health care and electronic commerce.

AB - We are investigating techniques for developing distributed and adaptive collections of information agents that coordinate to retrieve, filter and fuse information relevant to the user, task and situation, as well as anticipate user's information needs. In our system of agents, information gathering is seamlessly integrated with decision support. The task for which particular information is requested of the agents does not remain in the user's head but it is explicitly represented and supported through agent collaboration. In this paper we present the distributed system architecture, agent collaboration interactions, and a reusable set of software components for structuring agents. The system architecture has three types of agents: Interface agents interact with the user receiving user specifications and delivering results. They acquire, model, and utilize user preferences to guide system coordination in support of the user's tasks. Task agents help users perform tasks by formulating problem solving plans and carrying out these plans through querying and exchanging information with other software agents. Information agents provide intelligent access to a heterogeneous collection of information sources. We have implemented this system framework and are developing collaborating agents in diverse complex real world tasks, such as organizational decision making, investment counseling, health care and electronic commerce.

KW - Coordination

KW - Distributed AI

KW - Information agent

KW - Internet applications

KW - Software agent

UR - http://www.scopus.com/inward/record.url?scp=0000401537&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0000401537&partnerID=8YFLogxK

M3 - Article

VL - 5

SP - 181

EP - 211

JO - International Journal of Cooperative Information Systems

JF - International Journal of Cooperative Information Systems

SN - 0218-8430

IS - 2-3

ER -