Expert Agents Research Articles

Democracy as Inquiry, Inquiry as Democratic: Pragmatism, Social Science, and the Cognitive Division of Labor

One of the most distinctive features of pragmatism's conception of democracy is the strong connection that it makes between science and democracy. Not only must science be democratically organized, Dewey argues, but democracy must also be a form of inquiry that incorporates the cognitive division of labor. The pervasiveness of agent/principal relationships that results from the social organization of intelligence presents a problem for deliberative democracy. In order that deliberation can become more than mere discussion, the division of labor implies that it will sometimes be impossible for citizens to test the knowledge employed by experts. Using AIDS activism as an example, I propose that citizens will nonetheless be able to engage in public deliberation about the norms of cooperation between expert agents and lay principals, including even epistemic norms of validity, reliability, and evidence.

Will measuring instruments turn into agents?

The implications of agent based software engineering and Internet environment in the measurement practice are investigated. "Measurement-minded" expert agents and instrument-as-agent approaches offer numerous advantages. It would require, however, a reconsideration of certain properties of the measuring equipment and the role of the system controller.

Multi-agent system for cost estimation

The cost estimation now is a vital concern of every manufacturing firm, and many methods are available for cost estimation. In this paper , we build an novel architecture of multiagent system with each agent representing one kind of cost estimation method (distributed multi-agent system). The system first classifies the user's requests , then makes the expert agents to cooperate and compete to fulfill the task. The model is based on a fuzzy classification of cost estimation methods and a dynamic optimization of structure to make the agents to learn from the past (based on agent reputation). In this way, the amount of information exchange is considerably reduced.

Application of expert agents/assistants in library and information systems

This article presents a brief overview of expert agents and assistants, and then discusses activities in several areas of library and information centres where expert systems have been developed and where intelligent agents assistants could be of practical use in such activities. A discussion of what an intelligent agent or assistant might perform in these areas is outlined. http://dx.doi.org/10.14429/dbit.16.4.3274

Collaborative version control in an agent-based hypertext environment

In this work we discuss a number of issues for the design of hypertext systems in an agent-based model of computation. We examine how the “traditional” fundamental concepts which are at the basis of the design of hypertexts can be re-visited under a new perspective of collaborative expert agents. The paper presents how some principles of high-level concurrent programming are applied as new methodologies for the design and development of complex software, such as hypertext systems. By adopting an agent-based framework, we gain powerful control on version management that presents considerable difficulties for the development of hypertext systems; a general distributed version control mechanism is applied, without significant differences, both in single-user and in collaborative multiuser mode. In both cases, the underlying hypertext architecture is defined in terms of computational agents interacting each other in order to accomplish common goals. In this paper we present a first-level prototype implemented in a concurrent object-oriented language, realized on the top of the Common Lisp Object System.

Completeness and consistency checking of system requirements: An expert agent approach

Specifying requirements is one of the most critical activities in any systems development effort. It is extremely important that the requirements specified for a desired system are complete and consistent; users, however, experience great difficulty in doing that. The problem becomes especially acute when the intended system is very complex. In this paper, we propose a framework which employs expert agents to assist users in the requirements definition process. The approach is defined within the context of RAPID-WS, an object-oriented tool that supports the Air Force weapon systems requirements development process. We describe how an expert agent uses a knowledge base and a case base to assist a user in defining a complete and consistent set of system requirements. The agent generates a requirements hierarchy for the user to view and dynamically responds to any changes to requirements made by the user. By allowing control to switch freely back and forth between the user and the agent, the proposed approach provides a collaborative medium for requirements specification.

Machine learning and planning for data management in forestry

The Seidam project uses an AI planning-based approach that combines three problem-solving methods-transformational analogy, derivational analogy and goal regression-to automatically answer forest-management queries. The project is conducted under NASA's Applied Information Systems Research Program. Seidam, which runs on a Sun Sparcstation using the Solaris 2.3 version of Unix, is a complex system that relies on extensive cooperation between expert systems and processing agents.

Revolutionizing Definity® Call Centers in the 1990s

The award-winning AT&T DEFINITY® G3 Expert Agent Selection (EAS) feature has fundamentally changed the way in which call centers provide services for a variety of business applications. The skills-matching concept of EAS simplifies the problem of meeting incoming caller needs with trained call center agents. The Logical Agent part of EAS provides call center agents with an incentive for advancement while also providing newfound flexibility in how they perform their jobs. Both these EAS innovations are patented, with the skills-matching patent winning the 1995 AT&T Patent Recognition Award. This paper describes how EAS improves the efficiency of call centers, and it discusses the implementation approach used to realize this important new call center feature.

Jean Hyacinthe De Magellan, F. R. S., and the chemical revolution of the eighteenth century

Joã Jacinto de Magalhãs (1722-1790) left the congregation of Augustinian monks at Coimbra around 1755 to pursue a scientific career. Thereafter he became known generally, from his writings, as Jean Hyacinthe de Magellan. He became involved with the advance of science in his day when the French naval officer and astronomer, Gabriel de Bory (1720-1801), visited Portugal in 1751 to observe a solar eclipse and stayed at the monastery of Coimbra. Magellan served as Bory’s guide and assistant during the latter’s visit and, in turn, Bory was instrumental in introducing Magellan to a wide circle of leading European scientists and men of influence, particularly those of France. 1,2 Over the period 1755 to 1764, before taking up residence in London, Magellan travelled throughout Europe to make the acquaintance of scientists and patrons of science and the associated crafts, and to extend his linguistic skills. Magellan became an unpaid confidential agent of the French government, possibly during this period, reporting on major technical innovations introduced outside France: surviving letters show that he was engaged in such activities by 1770. The Director of the French Government’s bureau of commerce, Daniel Trudaine (1703-1769), made use of expert agents to discover the secrets of foreign industrial superiority, particularly British, and the practice was continued by his son, Trudaine de Montigny (1733-1777), who took over the directorship from his father in 1764. Soon after settling in London in 1764, Magellan was regularly sending the younger Trudaine packages of books and pamphlets describing new inventions and, on one occasion, he even endeavoured to smuggle out of England a newly developed loom that the British

Flute an Expert Floor Planner for Full-Custom VLSI Design

Flute is a heuristic floorplanner that operates as part of Cadre, a system of cooperating expert agents for converting a hierarchical structural description into full-custom VLSI layout. Flute is modeled on the human floorplanning process and uses a mixture of rule-based programming, state control, and algorithmic operators. Initially, a topological plan is generated by placing modules on a grid graph. From this plan, a constraint graph is prepared. This graph is solved to add geometric size and placement information to the floorplan. Though Flute handles a fairly small number of submodules at a time, it can construct a floorplan of complex VLSI layout using a hierarchical structure of ICs. Flute is implemented in Zeta-lisp on Symbolics Lisp machines.

Designing With Negotiation Using SingleFunction Agents

During cooperative, multi-agent, design problem-solving, disagreements may arise among the expert agents. These differences are resolved by Negotiation. This paper describes the design and implementation of an approach to handle negotiation between expert agents.