Mixed-Initiative Issues in an Agent-Based Meeting Scheduler
User Modeling and User-Adapted InteractionPublished 1 April 1999
Amedeo Cesta, Daniela D’Aloisi
Citations21
SJR quartileQ1
SJR score0.76
SNIP1.64
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
MASMA, an agent system for distributed meeting scheduling, is described, and the solutions developed to control interaction are explained in detail.
Abstract
This paper concerns mixed-initiative interaction between users and agents. After classifying agents according to their task and their interactivity with the user, the critical aspects of delegation-based interaction are outlined. Then MASMA, an agent system for distributed meeting scheduling, is described, and the solutions developed to control interaction are explained in detail. The issues addressed concern: the agent capability of adapting its behavior to the user it is supporting; the solution adopted to control the shift of initiative between personal agents, their users and other agents in the environment; the availability of features, e.g. the inspection mechanism, that endow the user with a further level of control to enhance his sense of trust in the agent.
Keywords
Computer Science
The Knowledge Engineering ReviewIntelligent agents: theory and practice
6,644 Citations1995Michael Wooldridge, Nicholas R. Jennings
The aim of this paper is to point the reader at what it is perceived to be the most important theoretical and practical issues associated with the design and construction of intelligent agents.
Computational LinguisticsAttention, intentions, and the structure of discourse
2,606 Citations1986Barbara J. Grosz, Candace L. Sidner
A new theory of discourse structure that stresses the role of purpose and processing in discourse is explored and various properties of discourse are described, and explanations for the behavior of cue phrases, referring expressions, and interruptions are explored.
Communications of the ACMAgents that reduce work and information overload
2,321 Citations1994Pattie Maes
Results from several prototype agents that have been built using an approach to building interface agents are presented, including agents that provide personalized assistance with meeting scheduling, email handling, electronic news filtering, and selection of entertainment.
KQML as an agent communication language
1,470 Citations1994Tim Finin, Richard Fritzson +2 more
The design of and experimentation with the Knowledge Query and Manipulation Language (KQML), a new language and protocol for exchanging information and knowledge, which is aimed at developing techniques and methodology for building large-scale knowledge bases which are sharable and reusable.
Communications of the ACMThe role of emotion in believable agents
1,149 Citations1994Joseph Bates
Appropriate timed and clearly expressed emotion is a central requirement for believable characters and how these ideas may apply to believable interactive characters, which are called believable agents are discussed.
Email overload
973 Citations1996Steve Whittaker, Candace L. Sidner
It is demonstrated that email overload creates problems for personal information manageaa, and how this arises is explained and technical solutions to the problem are proposed.
Why CSCW applications fail: problems in the design and evaluationof organizational interfaces
958 Citations1988Jonathan Grudin
Examination of several application areas reveals a common dynamic: a factor contributing to the application’s failure is the disparity between those who will benefit from an application and those who must do additional work to support it.
International Journal of Man-Machine StudiesTrust between humans and machines, and the design of decision aids
740 Citations1987Bonnie M. Muir
A definition and model of human-machine trust are proposed, and the dynamics of trust between humans and machines are examined and recommendations are made for calibrating users' trust in decision aids.
ComputerGarnet: comprehensive support for graphical, highly interactive user interfaces
470 Citations1990Brad A. Myers, Dario A. Giuse +6 more
The Garnet research project, which is creating a set of tools to aid the design and implementation of highly interactive, graphical, direct-manipulation user interfaces, is discussed.
Communications of the ACMA softbot-based interface to the Internet
452 Citations1994Oren Etzioni, Daniel S. Weld
The Internet Softbot (software robot) is a fullyimplemented AI agent developed at the University of Washington that uses a UNIX shell and the World-Wide Web to interact with a wide range of internet resources.
Communications of the ACMExperience with a learning personal assistant
410 Citations1994Tom M. Mitchell, Rich Caruana +3 more
The design of one particular learning assistant is described: a calendar manager, called CAP (Calendar APprentice), that learns user scheduling preferences from experience and suggests that machine learning methods may play an important role in future personal software assistants.
User Modeling and User-Adapted InteractionCOLLAGEN: A Collaboration Manager for Software Interface Agents
238 Citations1998Charles Rich, Candace L. Sidner
An application-independent collaboration manager, called Collagen, is implemented, based on the SharedPlan theory of discourse, and used to build a software interface agent for a simple air travel application that provides intelligent, mixed initiative assistance without requiring natural language understanding.
Mixed initiative in dialogue
219 Citations1990Marilyn Walker, Steve Whittaker
A set of rules for the transfer of control is applied to 4 sets of dialogues and it is found that both allocation of control and the manner in which control is transferred is radically different for the two dialogue types.
TRAINS-95: towards a mixed-initiative planning assistant
219 Citations1996George Ferguson, James F. Allen +1 more
The implementation of a prototype version of a mixed-initiative planning system, TRAINS-95, which helps a manager solve routing problems in a simple transportation domain, and how traditional planning technology does not play a major role in the system is described.
A robust system for natural spoken dialogue
211 Citations1996James F. Allen, Bradford W. Miller +2 more
An evaluation of the system using time-to-completion and the quality of the final solution suggests that most native speakers of English can use the system successfully with virtually no training.
User Modeling and User-Adapted InteractionLifelike Pedagogical Agents for Mixed-initiative Problem Solving in Constructivist Learning Environments
204 Citations1999James C. Lester, Brian Stone +1 more
Experience with focus group studies conducted with middle school students interacting with the implemented agent suggests that lifelike pedagogical agents hold much promise for mixed-initiative learning.
A layered architecture for office delivery robots
196 Citations1997Reid Simmons, Richard Goodwin +3 more
The architecture is composed of four abstraction layers: obstacle avoidance, navigation, path planning, and task scheduling, which are independent, communicating processes that are always active, processing sensory data and status information to up-date their decisions and actions.
Increasing believability in animated pedagogical agents
156 Citations1997James C. Lester, Brian Stone
A framework for dynamically sequencing animated pedagogical agents that inhabits a knowledge based learning environment and ronment for the domain of botanical anatomy and physiology is implemented in Herman the Bug.
COLLAGEN
150 Citations1997Charles Rich, Candace L. Sidner
This work has implemented a prototype toolkit, called Collagen, which embodies collaborative discourse principles, and takes the position that autonomous agents, when they interact with people, should be governed by the same principles that underlie human collaboration.
A learning interface agent for scheduling meetings
143 Citations1993Robyn Kozierok, Pattie Maes
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.
An autonomous spacecraft agent prototype
85 Citations1997Barney Pell, Douglas E. Bernard +6 more
A visual calendar for scheduling group meetings
77 Citations1990David V. Beard, Murugappan Palaniappan +4 more
A prototype of a priority-based, graphical scheduling system called Visual Scheduler (VS) is developed and a field study showed VS to be a generally useful system and provided valuable feedback on ways to enhance the functionality of the system to increase its value as a groupwork tool.
Models of plans to support communication: an initial report
77 Citations1990Karen E. Lochbaum, Barbara J. Grosz +1 more
The SharedPlan model of collaborative behavior is modified and expanded and an algorithm for updating an agent's beliefs about a partial SharedPlan is presented and an initial implementation of this algorithm is described in the domain of network management.
Software agents and user autonomy
72 Citations1997Batya Friedman, Helen Nissenbaum
A definition and rationale for user autonomy in relation to software agents are provided and a framework for understanding how user autonomy can be promoted or undermined through the design of software agents is described.
ACM Transactions on Information SystemsElectronic calendars in the office: an assessment of user needs and current technology
69 Citations1985Christine M. Kincaid, Pierre B. Dupont +1 more
A survey of office workers is carried out to examine their use both of paper calendars and of electronic calendars that are commercially available as part of integrated office systems, assessing the degree to which electronic calendars meet the needs of users.
International Journal of Human-Computer StudiesDelegating to software agents
61 Citations1997Allen E. Milewski, Steven H. Lewis
Issues regarding task delegation as they pertain to the design of intelligent-agent?user interfaces are described, which need to overcome well-established drawbacks in delegation.
An automated meeting scheduling system that utilizes user preferences
55 Citations1997Thomas Haynes, Sandip Sen +2 more
User Modeling and User-Adapted InteractionWhat is Initiative?
54 Citations1998Robin Cohen, Coralee Allaby +10 more
The paper concludes by summarizing some of the key points in common to the theories, and commenting on the inherent difficulties of the exercise, thereby elucidating the limitations which are necessarily encountered in designing such theories as the basis for designing mixed-initiative systems.
Annals of Operations ResearchA contracting model for flexible distributed scheduling
43 Citations1996Sandip Sen, Edmund H. Durfee
This paper uses the application domain of distributed meeting scheduling to investigate how agents embodying deeper domain knowledge can choose among alternative strategies for searching their calendars in order to create flexible schedules within reasonable cost.
Lifelike Pedagogical Agents for Mixed-Initiative Problem Solving in Constructivist Learning Environments
38 Citations1999James C. Lester, Brian Stone +1 more
Meet your destiny
37 Citations1994Eithan Ephrati, Gilad Zlotkin +1 more
Three scheduling mechanisms that are manipulation-proof for closed systems that maintains user privacy (for the most part), allows users to have the greatest influence on the resulting schedule and does not maintain user privacy.
Decision Support SystemsA mixed-initiative scheduling workbench integrating AI, OR and HCI
35 Citations1993Wen-Ling Hsu, Michael J. Prietula +2 more
This system weaves together numeric and symbolic computing techniques to form a ‘scheduler's workbench’ which supports an approach to problem solving the authors call mixed-initiative scheduling in which the human and the machine interact in a coherent and cooperative manner to solve complex production scheduling problems.
ACM SIGCHI BulletinBuilding interfaces as personal agents
21 Citations1996Amedeo Cesta, Daniel D'Aloisi
A solution is proposed based on the approaches of software agents and distributed architectures which concur in building a flexible and scalable environment that the user can access through intelligent agents that work as interfaces.
User Modeling and User-Adapted InteractionAn Approach to Mixed Initiative Spoken Information Retrieval Dialogue
20 Citations1999Eli Hagen
A dialogue planning algorithm is developed that distinguished between resources and routines and between the type and the content of an utterance and achieved a dialogue where the system adapts to the user's attempts at changing the direction of a dialogue.
Zenodo (CERN European Organization for Nuclear Research)A Framework for Filtering News and Managing Distributed Data.
16 Citations1997Giambattista Amati, Daniela D’Aloisi +2 more
ABIS, an intelligent agent for supporting users in ltering data from distributed and heterogeneous archives and repositories, is presented based on an adaptation of the generalized probabilistic model of information retrieval.
Mixed Initiative Interaction in O-Plan
11 Citations1997Austin Tate
This framework can form a basis for mixed initiative user/system agents working together to mutually constrain task descriptions and plans and to coordinate the taskoriented generation, refinement and enactment of those plans.
An Approach to Mixed Initiative Spoken Information Retrieval Dialogue
8 Citations1999Eli Hagen
Applied Neuropsychology AdultMixed-Initiative Interaction between Pedagogical Agents and Students in Virtual Environments
7 Citations1997Jeff Rickel, W. Lewis Johnson
Age and education were considered in the development of the normative data of the MMSE for the Portuguese population, and education level and age significantly contributed to the prediction of theMMSE scores and explained 26% of its variance.
Lecture notes in computer scienceTailorable interactive agents for scheduling meetings
3 Citations1998Amedeo Cesta, Marcello Collia +1 more
Capabilities are described that allow the interface agents that directly interact with users to customize their behaviors according to user preferences and to participate to multiple meeting negotiations following different contextual preferences.
Advances in human factors/ergonomicsActive interfaces for useful software tools
2 Citations1995Amedeo Cesta, Daniela D’Aloisi +1 more
A multi-agent implementation of an interface is proposed that from one side allows the user to easily specify his needs and from another actively reasons on the user's choices to improve the performance of the filtering process.