This page will
provide the Web resources regarding the publications of multiple aspects
of software agents research, such as introduction, design technology,
languages, etc.
General Introduction
Agent theories, architecture and
languages: a survey:
This paper discussed the
most important theoretical and practical issues associated with the
design and construction of intelligent agents. Agent theory is
concerned with the question of what an agent is, and the use of
mathematical formalisms for representing and reasoning about the
properties of agents. Agent architectures can be thought of as software
engineering models of agents. Agent languages are software systems for
programming and experimenting with agents; these languages typically
embody principles proposed by theorists. (By Michael J. Wooldridge,
Dept. of
Computing, Manchester Metropolitan University and Nicholas R. Jennings, Dept. of Electronic
Engineering, Queen Mary & Westfield College)
(PTF)
The Info Agent: an Interface for Supporting Users in Intelligent
Retrieval: In this paper we present a system that supports users in
retrieving data in distributed and heterogeneous archives and
repositories. The architecture is based on the metaphor of the software
agents and incorporates innovative hints from other fields: distributed
architectures, relevance feedback and active interfaces. (By Daniela
D'Aloisi and Vittorio Giannini, Fondazione Ugo Bordoni)
(HTML)
[TOP]
Agent Design & Architecture
Architecture-centric
object-oriented design method for multi-agent system:
This
paper introduces an architecture-centric object-oriented design method
for MAS (Multi-Agent Systems) using the extended UML (Unified Modeling
Language). The UML extension is
based on design principles that are derived from characteristics of MAS and concept of software architecture
which helps to design reusable and well-structured multi-agent
architecture. The extension allows one to use original object-oriented
method without syntactic or semantic changes which implies the
preservation of OO productivity, i.e., the availability of developers
and tools, the utilization of past experiences and knowledge, and the
seamless integration with other systems. (By Hongsoon Yim, Kyehyun
Cho, Jongwoo Kim, and Sungjoo Park)
(PDF)
Analysis and design multi-agent
system using MAS comonKADS:
This
article proposes an agent-oriented methodology called MAS-CommonKADS,
which extends the
knowledge engineering methodology CommonKADS with techniques from
object-oriented and protocol engineering methodologies. The methodology
consists of the development of seven models: Agent Model, Task
Model, Ex-pertise
Model, Organisation
Model, Coordination Model, Communication Model and Design
Model. (By Carlos A. Lglesias, Mercedes
Garijo ,Jos´ e C. Gonz´ alez and Juan R. Velasco)
(PDF)
Agent orientated analysis using
MESSAGE/UML: This paper
presents the MESSAGE/UML agent oriented software engineering methodology
and illustrates it on an analysis case study. The methodology covers MAS
analysis and design and is intended for use in mainstream software
engineering departments. MESSAGE extends UML by contributing agent
knowledge level concepts, and diagrams with notations for viewing them.
(By Giovanni Caire, Telecom Italia LAB; Francisco Leal, Paulo
Chainho, PT Inovação and Richard Evans, Broadcom Eireann Research Ltd)
(PDF)
Agent-Oriented Design:
This paper proposed a functional
decomposition of problem solving activities to serve as a framework to
assist MAS designers in their selection and integration of different
techniques and existing research results according to their system
requirements and presented a proposed model for the domain of naval
radar frequency management.
(HTML)
A Survey of Cognitive and Agent
Architectures: The paper provides some rational, structured
access to an analysis of cognitive and agent architectures. Twelve
architectures have been used for this preliminary analysis representing
a wide range of current architectures in artificial intelligence (AI).
The aim of the project is to facilitate both an understanding of current
architectures and provide insight to the development of future, improved
intelligent agent architectures.
(HTML)
Using Ontologies in the
multi-agent system: Multi-Agent
System (MAS) architectural framework allows human and software agents to
interoperate and thus cooperate within common application areas. Within
a MAS, the different "views of the world" of knowledgeable agents are to
be bridged through their commitment to common ontologies and
terminologies. Ontology and terminology servers providing other agents
with the common semantic foundation required for effective
interoperation, and allowing the configuration of suitable application
ontologies for distributed applications.
(HTML)
[TOP]
Agent Communication &
Collaboration
Modeling, communication, and
translation in the ACL project:
This paper discusses three
issues that are central to the ACL project, such as the necessity
to communicate the inheritance and constituency relationships, the
Ontolingua, a system for creating portable ontologies comparing them to
the CMU Object Model Specification Language and the translation of
vocabulary. (By Taha
Khedro, Daniel Malmer, Michael Genesereth, and Paul Teicholz, 1995)
(HTML)
The Agent Collaboration
Environment, an Assistant for Architects and Engineers:
This
Agent Collaboration Environment (ACE) provides the infrastructure for a
community of cooperative agents to assist a team of users. In contrast
to traditional blackboard systems, agents are organized into business
processes to reflect differences in tasks and workflow between users
from different disciplines and/or organizations.
(HTML)
Cooperation-ware: integration of
human collaboration with agent-based interaction:
This
paper presents a platform that integrates cooperation facilities for the
most important types of interaction. 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.
(HTML)
Collaborative interface agent:
This
paper focus on the research on the Learning interface agents, which
employ machine learning techniques to provide assistance to a user
dealing with a particular computer application. The learning techniques
achieved a level of personalization impossible with knowledge
engineering, and without the user intervention required by rule-based
systems. In order to address the problems of long "learning
curve" of such techniques, a collaborative solution that
experienced agents can help a new agent come up to speed quickly as well
as help agents in unfamiliar situations was proposed.
(HTML)
Coordination of multiple
intelligent software agents:
this paper investigated the 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, The paper also present the distributed system architecture,
agent collaboration interactions, and a reusable set of software
components for structuring agents.
(HTML)
[TOP]
Agent-oriented Software
Engineering
A framework for modeling
agent-oriented software:
This
paper introduce an extension of G-Nets, agent-based G-Net, as a generic
model for agent design, and progress from an agent-based design model to
an agent-oriented model, new mechanisms to support inheritance
modeling In addition, an agent family in electronic commerce is
provided in order to illustrate the formal modeling technique for
multi-agent systems. (By Haiping Xu
and Sol M. Shatz, Department of Electrical Engineering and Computer
Science, The University of Illinois at Chicago)
(PDF)
Agent-Oriented Software
Engineering: This paper
argued that the conceptual apparatus of agent-oriented systems was
well-suited to building software solutions for complex systems and
agent-oriented approaches represent a genuine advance over the current
state of the art for engineering complex systems. Based on view, the paper highlighted and
discussed the major issues raised by adopting an agent-oriented
approach to software engineering. (By Nicholas R. Jennings, Michael
Wooldridge, 2000. Proceedings of the 9th European Workshop on
Modelling Autonomous Agents in a Multi-Agent World : Multi-Agent System
Engineering (MAAMAW-99))
(PDF)
Determining When to Use an
Agent-Oriented Software Engineering Paradigm:
This paper
discussed the approach to determine the criteria and technique to
assist software engineers to select appropriate software engineering
methodology. (By Scott A. O’Malley 1 and Scott A. DeLoach 2001. Proceedings
of the Second International Workshop On Agent-Oriented Software
Engineering (AOSE-2001), Montreal, Canada, May 29th 2001.)
(PDF)
Agent-Oriented
Software Engineering: The
State of the Art : This paper discussed that the intelligent
agents and multi-agent system are the tools of software engineering, by
reviewing what is meant by the term "agent". The paper also
examined a number of a number of prototype techniques proposed for
engineering agent systems, including methodologies for agent-oriented
analysis and design, formal specification and verification methods for
agent systems, and techniques for implementing agent specifications. (By
Michael Wooldridge, Paolo Ciancarini, 2000.)
[TOP]
Agent Automation
Autonomy: specification,
measurement, and dynamic adjustment:
This
paper introduced the definition of the autonomy of the agents, discuss
the autonomy representation as well as the autonomy constraints.
(HTML)
Modeling Adaptive Autonomous
Agents: This paper extracts the main idea of the new approach of
building adaptive autonomous agents in artificial intelligence research,
evaluates its contributions, and identify its current limitations and
open problems.
(HTML)
IBHYS: A New Approach to Learn Users
Habits:
this paper introduces a new approach which is
particularly suited for learning interface agents because it provides an
incremental algorithm with low training time and decision time, which
does not require, from the designer of the interface agent, to de-scribe
in advance and quite carefully the repetitive patterns searched. This
approach limits the hypothesis search to a small portion of the
hypothesis space by letting each training example build a local
approximation of the global target function.
(HTML)
[TOP]
Agent
Application
An application of intelligent
and mobile agent in visual mining and e-commerce in the internet:
This
paper present an agent-based
system architecture for information retrieval and visualization on the
Internet, focusing on the development of a multi-agent-based
problem-solving strategy. Important features of the architecture are the
use of mobile agents as a device for searching and navigating through
distributed data, and the ability to present results using visual
techniques.
(HTML)
[TOP]
|