The Design of a Proactive Personal Agent for Task Management

Abstract

Personal assistant agents capable of proactively offering assistance can be more helpful to their users through their ability to perform tasks that otherwise would require user involvement. This article characterizes the properties desired of proactive behavior by a personal assistant agent in the realm of task management and develops an operational framework to implement such capabilities. We present an extended agent architectural model that features a meta-level layer charged with identifying potentially helpful actions and determining when it is appropriate to perform them. The reasoning that answers these questions draws on a theory of proactivity that describes user desires and a model of helpfulness. Operationally, assistance patterns represent a compiled form of this knowledge, instantiating meta- * Authors listed in reverse alphabetical order. 1250004-1N. Yorke-Smith et al.reasoning over the agent's beliefs about its user's activities as well as over world state. The resulting generic framework for proactive goal generation and deliberation has been implemented as part of a personal assistant agent in the computer desktop domain.

Human–agent teamwork in dynamic environments

“…Some agent systems support people with individual tasks (e.g. personal assistant agents in the realm of task management (Yorke-Smith et al, 2009) or in electronic commerce applications (Kamar et al, 2008;Rajarshi et al, 2001)), others support people who have to work in teams (e.g. multiagent teams that train incident commanders for large scale disasters (Schurr et al, 2006), or intelligent agents that support bidding decisions and negotiations (Pommeranz, Brinkman, Wiggers, Broekens & Jonker, 2009). )…”

“…Agents can play a variety of roles in their interactions with humans: they can support people in their tasks, for instance in collaborative interfaces and cognitive care systems (Shieber, 1996;Babaian, Grosz & Shieber, 2002;Yorke-Smith, Saadati, Myers & Morley, 2009); serve as proxies for individual people or organizations, for example as bidders in online auctions (Kamar, Horvitz & Meek, 2008;Rajarshi, Hanson, Kephart & Tesauro, 2001); or work autonomously to carry out tasks for which they are responsible, in settings such as computer games and simulation systems for natural disaster relief (Schurr, Patil, Pighin & Tambe, 2006;Murphy, 2004).…”

Realizing Networks of Proactive Smart Products

“…In particular, a key requirement for smart products imposed by our scenarios is that they need to be able to exhibit proactivity, both to improve the level of assistance to users and also to be able to co-operate effectively with other smart products in shared task scenarios. Proactivity can be informally characterized as the ability of a smart product to take initiative and perform some action, without having been specifically instructed to do so by a user or another smart product [2]. In addition, in order to be able to form and join networks with other smart products and engage in co-operative problem solving, smart products must also be capable of self-organisation.…”

PROBABILISTIC PLAN RECOGNITION FOR INTELLIGENT INFORMATION AGENTS - Towards Proactive Software Assistant Agents

“…Due to the amount of needed information and the constraints that the decisions must be made urgently the user can be cognitive overloaded, resulting in low quality decisions. In order to assist cognitively overloaded users, research on intelligent software agents has been vigorous, as illustrated by numerous recent projects (Chalupsky et al, 2002;Freed et al, 2008;Yorke-Smith et al, 2009).…”