p67-lieberman

p67-lieberman - CHI 97 * 22-27 MARCH 1997 PAPERS Autonomous...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: CHI 97 * 22-27 MARCH 1997 PAPERS Autonomous Interface Agents Henry Lieberman Media Laboratory Massachusetts Institute of Technology Cambridge, Mass 02139 USA. +1 6172530315 [email protected] ABSTRACT Two branches of the trend towards “agents” that are gaining currency are inre~ace agents, software that actively assists a user in operating an interactive interface, and autonomous agents, software that takes action without user intervention and operates concurrently, either while the user is idle or taking other actions. These two branches are related, but not identical, and are often lumped together under the single term “agent”. Much agent work can be classified as either being an interface agent, but not autonomous, or as an autonomous agent, but not operating directly in the interface. We show why it is important to have agents that are both interface agents and autonomous agents. We explore some design principles for such agents, and illustrate these principles with a description of Letizia, an autonomous interface agent that makes real-time suggestions for Web pages that a user might be interested in browsing. Keywords Agents, interface agents, autonomous agents, Web, browsing, search, learning. INTRODUCTION The definition of an agent is the subject of much controversy in the field of Human-Computer Interaction. While it is not our purpose here to settle this question, we are interested in the relationship between two particular aspects of agents. First, that the agent operate in the inte~ace, as opposed to in the background or “back end” of an application. Second, that the agent act autonomously, as opposed to having a sequential conversation with the user. Often, an agent will satisfy one or the other of these characteristics, but it is rare that it will exhibit both at once. Permission to mske digittl’hmd copies 01’01[or pall ot’this nmterill for pwsonzl or cl:mwcwm use is grmn(ed!vithout Ike provided IhaI [he copies me not made or dislnhuted for profit or wmmerml advmtage. k copy- righ( noIicc. Ilw ti!le of the puhlicnt ion :Il]d its dtk appear, and notice is glvell lhal Copy’righl IS hy permission ot’the ACht, ]nc, To copyotlwrwis~, to republish, to post nn scfiwrx or LOredistnhutc to Iisis. Irequiresspecific pwrmssiol] mdbr kc (211197. AIl;Im:I GA {: S)\ Copyright 1997 .AChf 0-89791-802-9/97/03 ..$’3.50 Traditional interface design is oriented toward conversational interfaces, where the user and the agent “take turns” acting. Autonomous interface agents lead to a somewhat diffenmt design style, brought on by the possibility that the agent may need to interact with the interface while the user is also interacting with the interface. The user may or may not be aware of the agent’s activities at any given moment. This design stvle has its own considerations and tradeoffs, and dese”mes ‘more attention in the interface design field....
View Full Document

This note was uploaded on 02/24/2010 for the course COMM 4400 at Cornell.

Page1 / 8

p67-lieberman - CHI 97 * 22-27 MARCH 1997 PAPERS Autonomous...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online