Article

Desktop Agent Manager (DAM): Decision Mechanism

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Desktop software agents are background processes that notify a computer user of certain predefined events. The complexity of desktop computing is increasing due to the proliferation of software agents. A desktop agent manager (DAM) may become an important component of desktop computing. This article focuses on the decision mechanism for the DAM to decide which agents should be allowed to access the user, which agents' results should be stored for future review by the user, and which of the agents should be filtered out. We prove the validity of the concept of a DAM by developing an architecture that includes both a prototype of the DAM and a simulator of various types of agents. In this article, we present the results of our simulations and analyses of the DAM decision mechanism.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Hence, the activity engagement variable considers only the social engagement of the user in his/her current task [17, 19]. The activity engagement variable is related to what has been previously considered as interruption threshold [11, 13], which also relates to the current activity type [29]. Ercolini and Kokar's [13] four levels of interruptibility threshold can be combined to the four levels of activity engagement, when considering workload and social engagement as having two levels (see Figure 2). ...
... The activity engagement variable is related to what has been previously considered as interruption threshold [11, 13], which also relates to the current activity type [29]. Ercolini and Kokar's [13] four levels of interruptibility threshold can be combined to the four levels of activity engagement, when considering workload and social engagement as having two levels (see Figure 2). Lastly, in InterruptMe [28] one of the factors was named activity engagement. ...
Conference Paper
This paper presents an organized set of variables that can aid intelligent privacy agents in predicting the best and necessary moments to interrupt users in order to give them control and awareness over their privacy, avoiding information overload or over choice.
... One possible solution to overcoming these problems rests in the advent of agent technology. A software agent can be defined as "an autonomous background process that communicates with both the user and other programs" (Ercolini & Kokar, 1997). Rooted in artificial intelligence research, agents are used to conduct routine tasks, search and retrieve information, support decision making, and act as domain experts. ...
... The use of software agents can contribute toward the advance of intelligent human-machine interaction (Kolski & Le Strugeon, 1998), which implies that (a) agents could incorporate knowledge of the task the user must perform and (b) adapt to the preferences and needs of the human user. The role of agents in desktop applications has been increasing over the past two decades or so (Ercolini & Kokar, 1997). ...
Article
This article presents the results of experimental evaluation of the effectiveness of agent support in e-negotiations. The agent-enhanced e-negotiation system eAgora has been used in the experiments. The system features an agent that assists the user in generating candidate offers, evaluating and critiquing incoming offers, and critiquing counteroffers. The work investigates the effects of agent support and task complexity on negotiation performance and perceived measures of usefulness, satisfaction, ease of use, and confidence. Overall, the results support the expectation that use of an agent leads to higher level of negotiation effectiveness, in particular for higher complexity tasks.
... Our formal approach to the treatment of uncertainty in fusion systems has been addressed in [61]. We have conducted research in the area of intelligent agents that can reason about their goals and actions in [62]. In [63] we defined an extension to the UML meta-model, which would allow for the translation of UML formalized information to the representation in DAML (DARPA Agent Markup Language). ...
Conference Paper
Full-text available
Interface agents are computer programs that employ Artificial Intelligence techniques in order to provide assistance to a user dealing with a particular computer application. The paper discusses an interface agent which has been modelled closely after the metaphor of a personal assistant. The agent learns how to assist the user by (i) observing the user's actions and imitating them, (ii) receiving user feedback when it takes wrong actions and (iii) being trained by the user on the basis of hypothetical examples. The paper discusses how this learning agent was implemented using memory-based learning and reinforcement learning techniques. It presents actual results from two prototype agents built using these techniques: one for a meeting scheduling application and one for electronic mail. It argues 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. The paper also argues what the advantages are of the particular learning techniques used.
Article
Full-text available
. This paper proposes, characterizes andoutlines the benefits of a new computer levelspecifically for multi-agent problem solvers. Thislevel is called the cooperation knowledge level andinvolves describing and developing richer and moreexplicit models of common social phenomena. Wethen focus on one particular form of social interactionin which groups of agents decide they wish to worktogether, in a collaborative manner, to tackle acommon problem. A domain independent model(called...
Article
Full-text available
The Envoy Framework addresses a need for computer-based assistants or agents that operate in conjunction with users' existing applications, helping them perform tedious, repetitive, or time-consuming tasks more easily and efficiently. Envoys carry out missions for users by invoking envoy-aware applications called operatives and inform users of mission results via envoy-aware applications called informers. The distributed, open architecture developed for Envoys is derived from an analysis of the best characteristics of existing agent systems. This architecture has been designed as a model for how agent technology can be seamlessly integrated into the electronic desktop. It defines a set of application programmer's interfaces so that developers may convert their software to envoy-aware applications. A subset of the architecture described in this paper has been implemented in an Envoy Framework prototype.
Article
Full-text available
We present a general theory that captures the relationship between certain domains and negotiation mechanisms. The analysis makes it possible to categorize precisely the kinds of domains in which agents find themselves, and to use the category to choose appropriate negotiation mechanisms. The theory presented here both generalizes previous results, and allows agent designers to characterize new domains accurately.
Article
Computer systems based on cooperating agent architectures are currently introduced in industrial process supervision and control applications as operator support systems in tasks such as fault diagnosis, system restoration etc. Cooperating agents are relevant to these applications since they involve a high degree of physical distribution, the operators' decisions are often based on multiple conflicting views which can be moderated by the cooperating agents, and the domains are complex with high degree of modularity.In the frame of the research project ARCHON, a multi-agent system architecture has been defined in order to be used in industrial process supervision and control applications. An issue of high importance in this context is the interaction with the human operator and the design of a user interface which supports this interaction. The impact of multi-agent architectures on the user interface design of industrial process supervision and control systems is the subject of this paper. An example of an interface designed for a multi-agent system in the area of electrical network supervision is provided.
Article
As intelligent systems become more pervasive and capture more expert and organizational knowledge, the expectation that they be integrated into larger problem-solving systems is heightened. To capitalize on these investments and more fully exploit their potential as knowledge repositories, general principles for their integration must be developed. Although simulated and prototype systems described in the literature provide solutions to some practical problems, most are empirical (or often simply intuitive) in design, emerging from implementation strategy instead of general principles. As a step toward the development of such principles, this paper presents a taxonomy for multi-agent systems that defines alternative architectures based on fundamental distributed, intelligent system characteristics.
Article
The CUBRICON Intelligent Window Manager (CIWM) is a knowledge-based system that automates windowing operations. The CIWM is a component of CUBRICON, a prototype knowledge-based multi-media human-computer interface. CUBRICON accepts inputs and generates outputs using integrated multiple media/modalities including speech, printed/typed natural language, tables, forms, maps, graphics, and pointing gestures. The CIWM automatically performs window management functions on CUBRICON's color and monochrome screens. These functions include window creation, sizing, placement, removal, and organization. These operations are accomplished by the CIWM without direct human inputs, although the system provides for user override of the CIWM decisions.
Magnet 1.0 intelligent agent-based utility. Mncumrld
  • F Tessler
Tessler, F. (1993). Magnet 1.0 intelligent agent-based utility. Mncumrld, 10,220.
Open Sesame! summons agents to automate tasks
  • A Streeter
Streeter, A. (1993). Open Sesame! summons agents to automate tasks. MacWEEK, 7, 1-2.
Agent technology: The fine line hetween smart design and intelligent software
  • M Milev
Milev, M. (1993). Agent technology: The fine line hetween smart design and intelligent software. MncWEEK, 7,4145.
Aft architecttrre for a desktop agent mannger
  • D A G Ercolini
Ercolini, D. A. G. (1994). Aft architecttrre for a desktop agent mannger. Unpuhlished master's thesis, Northeastern University, Boston.
Euokriltg agents for perso~rnlized informntionfilteriitg. Paper presented at the 9th
  • B Sheth
  • P Maes
Sheth, B., & Maes, P. (1993, March). Euokriltg agents for perso~rnlized informntionfilteriitg. Paper presented at the 9th IEEE Conferenceon Artificial Intelligence for Applications, Orlando, Fl.. .
Agent technology: The fine line hetween smart design and intelligent software
  • P Maes
  • R Kozierok
Maes, P., & Kozierok, R. (1993). Learning interface agents. Proceedirrgs ofAAAI '93,459465. Milev, M. (1993). Agent technology: The fine line hetween smart design and intelligent software. MncWEEK, 7,4145.
Euokriltg agents for perso~rnlized informntionfilteriitg. Paper presented at the 9th IEEE Conferenceon Artificial Intelligence for Applications
  • B Sheth
  • P Maes
Sheth, B., & Maes, P. (1993, March). Euokriltg agents for perso~rnlized informntionfilteriitg. Paper presented at the 9th IEEE Conferenceon Artificial Intelligence for Applications, Orlando, Fl.. . -
Magnet 1.0 intelligent agent-based utility. Mncumrld, 10,220
  • F Tessler
  • G Zlotkin
  • J Rosenschein
Tessler, F. (1993). Magnet 1.0 intelligent agent-based utility. Mncumrld, 10,220. Zlotkin, G., & Rosenschein, J. (1993). A domain theory for task oriented negotiation. Proceed-in@ of lJCn1'93.416422.