Agents that reduce work and information overload

  title={Agents that reduce work and information overload},
  author={Pattie Maes},
  journal={Commun. ACM},
  • P. Maes
  • Published 1 July 1994
  • Computer Science
  • Commun. ACM
Publisher Summary Computers are becoming the vehicle for an increasing range of everyday activities. [] Key Result It presents results from several prototype agents that have been built using this approach, including agents that provide personalized assistance with meeting scheduling, email handling, electronic news filtering, and selection of entertainment.

Intelligent Software Agents with Applications in Focus

The concept of an agent has become important in a diverse range of sub-disciplines of IT, including software engineering, networking, mobile systems, control systems, decision support, information recovery and management, e-commerce, and many others.

Designing More Interactive Interface Agents

A model for designing agents which are more or less autonomous, but which recognize opportunities for initiating communication with their users in order to garner further useful information is proposed, which makes these agents more interactive, allowing them to take the initiative to solicit further input from the user, toward improving their overall performance.

Software Agents and .gencg: Personat Information Hanagement Perspective

A user-driven approach to the design of agent- based systems is presented and it is argued that agent systems will only be successful if both users and their tasks act as the bases for the designs of such systems.

User Environments and Individuals: Experience with Adaptive Interface Agents

This paper documents the development of a set of classes which implement an architecture for adaptive interfaces, intended to be used as part of larger user interface systems which are to exhibit adaptive behaviour.

M: an architecture of integrated agents

M, a software assistant, is a software system that integrates muhi-pie " reasoning agents " whose collab-orative results serve to assist a user working together with other individuals in a desktop multimedia conferencing environment.

Personalizing user-agent interaction

Autonomous Agents for Initiating Communication in Internet Community Chat Rooms

This paper addresses a framework for a multiagent-supported community chat room that supports that an agent is able to observe the actions of the user and recommend chat rooms or specific conversations in chat rooms based on its understanding of the users.

A study of software agent design and implementation

The thesis provides a frame for agents' development, which allows the construction of agents that meet these criteria, and emphasised that through design and implementation to testing and maintenance, user's needs and user's satisfaction should always be the main concern of agent's designers.

Software (intelligent) Agents Why Software Agents for Ec, Especially Now? Information Overload Delegate, Do Not Navigate

  • Computer Science
As various chapters in the text demonstrate, software agents have come to play an increasingly important role in EC—providing assistance with Web searches, helping consumers comparison shop, and automatically notifying users of recent events (e.g., new job openings).

An Interface Agent Approach to Personalize Users' Interaction with Databases

This work has developed an agent, named QueryGuesser, to assist users of computer applications in which retrieving information from a database is a key task, and observes a user's behavior while he is working with the database and builds the user's profile.

Collaborative Interface Agents

A framework for multi-agent collaboration is presented, results of a working prototype, based on learning agents for electronic mail are discussed, and a major problem with the learning approach is that the agent has to learn from scratch and thus takes some time becoming useful.

Learning Interface Agents

It is argued that the machine learning approach to building interface agents is a feasible one which has several advantages over other approaches: it provides a customized and adaptive solution which is less costly and ensures better user acceptability.

A learning approach to personalized information filtering

Experimental results indicate that Newt can be personalized to serve some of the news ltering needs of the user, in particular, those that are more regular and predictable, and the basic framework for personalized information ltering agents is presented.

A learning interface agent for scheduling meetings

The experimental data reported upon demonstrate that the learning approach to building intelligent interface agents is a very promising one which has several advantages over more standard approaches.

Object lens: a “spreadsheet” for cooperative work

The combination of these primitives provides a single consistent interface that integrates facilities for object-oriented databases, hypertext, electronic messaging, and rule-based intelligent agents.

Evolving agents for personalized information filtering

  • B. ShethP. Maes
  • Computer Science
    Proceedings of 9th IEEE Conference on Artificial Intelligence for Applications
  • 1993
Results of a set of experiments are presented in which a small population of information filtering agents was evolved to make a personalized selection of news articles from the USENET newsgroups, showing that the artificial evolution component of the system is responsible for improving the recall rate of the selected set of articles, while learning from feedback component improves the precision rate.

A Personal Learning Apprentice

The organization of CAP, its performance in initial field tests, and more general lessons learned from this effort about learning apprentice systems are described.

The Architecture Machine: Toward a More Human Environment

The use of computers to aid the architectural designer and urban planner is already beyond the experimental stage and part of the workaday routine of many professionals. There are, for example,

EAGER: programming repetitive tasks by example

Abstract Eager utilizes a new interface technique, called anticipation, to show how it has generalized: when it detects a repetitive activity, it highlights menus and objects on the screen to indicate what it expects the user to do next.

Creating user interfaces by demonstration

Peridot, a new User Interface Management System, addresses this problem by allowing the user interface designer to demonstrate how the input devices should be handled by giving an example of the interface in action.