Abstract
Intelligent personal assistants (IPAs) are playing an increasingly significant role in our everyday lives. However, their reactive behaviour limits their assistance to a user’s explicit requests. Integrating proactivity in these assistants would allow them to perform tasks on behalf of users without an explicit request and, in turn, improve the user experience. To explore this goal, this work presents MAIS (Multi Agent Interactions Simulator) which is capable of generating simulations of proactive agents. MAIS allows us to study the behaviour of agents, their interactions with each other in a multi-agent environment, and the importance of different agent features to accomplish a particular task. This paper presents the results from my experiments for a use case based on meeting scheduling in an organisational setting and the potential opportunities and challenges related to the adoption of IPAs. Human-in-the-loop control is introduced as a key component and the challenges arising with varying levels of autonomy in agents are also studied.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Meneguzzi, F., Oh, J.: Proactive Assistant Agents, Papers from the 2010 AAAI Fall Symposium, Arlington, Virginia, USA, 11–13 November 2010, AAAI Technical Report, vol. FS-10-07 (2010)
de Barcelos Silva, A., et al.: Intelligent personal assistants: a systematic literature review. Expert Syst. Appl. 147(C), 113–193 (2020)
Enge, E.: The rise of personal assistants (2017)
Georgeff, M., Pell, B., Pollack, M., Tambe, M., Wooldridge, M.: The Belief-Desire-Intention Model of Agency. In: Müller, J.P., Rao, A.S., Singh, M.P. (eds.) ATAL 1998. LNCS, vol. 1555, pp. 1–10. Springer, Heidelberg (1999). https://doi.org/10.1007/3-540-49057-4_1
Islas-Cota, E., Gutierrez-Garcia, J.O., Acosta, C.O., Rodríguez, L.F.: A systematic review of intelligent assistants. Fut. Gener. Comput. Syst. 128(C) (2022)
Jeromela, J.: Scrutability of intelligent personal assistants. In: Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2022, pp. 335–340. ACM, New York, NY, USA (2022)
Lopatovska, I.: Overview of the intelligent personal assistants. Ukr. J. Lib. Inf. Sci. 72–79 (2019)
Lopes, F., Coelho, H.: Negotiation and Argumentation in Multi-agent Systems: Fundamentals, Theories, Systems and Applications, Bentham Science Publisher, December 2014
Mark, W.G., Perrault, R.: Calo: Cognitive assistant that learns and organizes
Meurisch, C., Ionescu, M.D., Schmidt, B., Mühlhäuser, M.: Reference model of next-generation digital personal assistant: Integrating proactive behavior. In: Conference: the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2017 ACM International Symposium on Wearable Computers, UbiComp 2017, ACM (2017)
Myers, K., et al.: An intelligent personal assistant for task and time management. AI Mag. 28(2), 47 (2007). Jun
O’Leary, D.E.: Google’s duplex: pretending to be human. Int. J. Intell. Syst. Acc. Financ. Manage. 26(1), 46–53 (2019)
Siebers, P.O., Aickelin, U.: Introduction to multi-agent simulation, March 2008
Sun, Y., Yuan, N.J., Wang, Y., Xie, X., McDonald, K., Zhang, R.: Contextual intent tracking for personal assistants. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016)
Tambe, M.: Electric elves: what went wrong and why. AI Mag. 29(2) (2008)
Yorke-Smith, N., Saadati, S., Myers, K.L., Morley, D.N.: The design of a proactive personal agent for task management. Int. J. Artif. Intell. Tools 21 (2012)
Acknowledgements
This research was conducted with the financial support of Science Foundation Ireland [13/RC/2106_P2] at ADAPT, the SFI Research Centre for AI-Driven Digital Content Technology at Trinity College Dublin, The University of Dublin.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Akbar, A. (2022). Proactivity in Intelligent Personal Assistants: A Simulation-Based Approach. In: Baumeister, D., Rothe, J. (eds) Multi-Agent Systems. EUMAS 2022. Lecture Notes in Computer Science(), vol 13442. Springer, Cham. https://doi.org/10.1007/978-3-031-20614-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-20614-6_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20613-9
Online ISBN: 978-3-031-20614-6
eBook Packages: Computer ScienceComputer Science (R0)