Seven Aspects of Mixed-Initiative Reasoning:An Introduction to this Special Issue on Mixed-Initiative Assistants

AI Magazine

Mixed-initiative assistants are agents that interact seamlessly with humans to extend their problem-solving capabilities or provide new capabilities. Developing such agents requires the synergistic integration of many areas of AI, including knowledge representation, problem solving and planning, knowledge acquisition and learning, multiagent systems, discourse theory, and human-computer interaction. This paper introduces seven aspects of mixed-initiative reasoning (task, control, awareness, communication, personalization, architecture, and evaluation) and discusses them in the context of several state-of-the-art mixed-initiative assistants. The goal is to provide a framework for understanding and comparing existing mixed-initiative assistants and for developing general design principles and methods.



A Mixed-Initiative System for Building Mixed-Initiative Systems

AAAI Conferences

Mixed-initiative assistants can be applied to a variety of information-rich problem-solving tasks on the Web, such as travel planning and equipment purchasing tasks. A mixed-initiative environment for such tasks can greatly improve the decision making environment for a user if the application is designed to meet the needs of a user. However, each user has different needs and preferences, making it difficult to design a single application for all users. Thus, we are applying the mixed-initiative paradigm recursively to develop a mixed-initiative system for building mixed-initiative systems. This paper describes the basic framework for constructing mixedinitiative systems, which is based on our previous work on developing mixed-initiative information assistants in Heracles. The new system, called Alcmene, will be implemented as an application of Heracles and will allow a user to author a new Heracles application through a mixed-initiative problem-solving process.


1928

AI Magazine

Mixed-initiative assistants are agents that interact seamlessly with humans to extend their problem-solving capabilities or provide new capabilities. Developing such agents requires the synergistic integration of many areas of AI, including knowledge representation, problem solving and planning, knowledge acquisition and learning, multiagent systems, discourse theory, and human-computer interaction. This paper introduces seven aspects of mixed-initiative reasoning (task, control, awareness, communication, personalization, architecture, and evaluation) and discusses them in the context of several state-of-the-art mixed-initiative assistants. The goal is to provide a framework for understanding and comparing existing mixed-initiative assistants and for developing general design principles and methods. Mixed initiative assumes an efficient, natural interleaving of contributions by users and automated agents that is determined by their relative knowledge and skills and the problem-solving ...


Mixed-Initiative in Computer Games: Algorithmic Content Creation in Open-ended Worlds

AAAI Conferences

We provide a general definition of mixed-initiative for application to the area of computer games. This definition is used to provide a survey of the ways in which mixedinitiative has been applied to games up to this point, and where and how mixed-initiative could be applied to improve the quality of games in the future. The need for algorithmic content creation though mixed-initiative interactions is demonstrated, and the application of mixed-initiative interactions to the challenge of developing realistic interactions with computer-controlled agents in an openended roleplaying game is analyzed.