Reasoning with commonsense science knowledge is an important challenge for Artificial Intelligence. This paper presents a system that revises its knowledge in a commonsense science domain by constructing and evaluating explanations. Domain knowledge is represented using qualitative model fragments, which are used to explain phenomena via model formulation. Metareasoning is used to (1) score competing explanations numerically along several dimensions and (2) evaluate preferred explanations for global consistency. Inconsistencies cause the system to favor alternative explanations and thereby change its beliefs. We simulate the belief changes of several students during clinical interviews about how the seasons change. We show that qualitative models accurately represent student knowledge and that our system produces and revises a sequence of explanations similar those of the students.

Evidence indicates that episodic memory plays an important role in general cognition. A modest body of research exists for creating artificial episodic memory systems. To date, research has focused on exploring their benefits. As a result, existing episodic memory systems rely on a small, relevant memory cue for effective memory retrieval. We present Ziggurat, a domain-independent episodic memory structure and accompanying episodic learning algorithm that learns the temporal context of recorded episodes. Ziggurat's context-based memory retrieval means that it does not have to rely on relevant agent cues for effective memory retrieval; it also allows an agent to dynamically make plans using past experiences. In our experimental trials in two different domains, Ziggurat performs as well or better than an episodic memory implementation based on most other systems.

This paper documents a functionality-driven exploration of automatic working-memory management in Soar. We first derive and discuss desiderata that arise from the need to embed a mechanism for managing working memory within a general cognitive architecture that is used to develop real-time agents. We provide details of our mechanism, including the decay model and architecture-independent data structures and algorithms that are computationally efficient. Finally, we present empirical results, which demonstrate both that our mechanism performs with little computational overhead and that it helps maintain the reactivity of a Soar agent contending with long-term, autonomous simulated robotic exploration as it reasons using large amounts of acquired information.

Researchers have studied problems in metacognition both in computers and in humans. In response some have implemented models of cognition and metacognitive activity in various architectures to test and better define specific theories of metacognition. However, current theories and implementations suffer from numerous problems and lack of detail. Here we illustrate the problems with two different computational approaches. The Meta-Cognitive Loop and Meta-AQUA both examine the metacognitive reasoning involved in monitoring and reasoning about failures of expectations, and they both learn from such experiences. But neither system presents a full accounting of the variety of known metacognitive phenomena, and, as far as we know, no extant system does. The problem is that no existing cognitive architecture directly addresses metacognition. Instead, current architectures were initially developed to study more narrow cognitive functions and only later were they modified to include higher level attributes. We claim that the solution is to develop a metacognitive architecture outright, and we begin to outline the structure that such a foundation might have.

Social cognition is a key feature of human-level intelligence. However, social reasoning faculties are rarely included in cognitive systems. To encourage research in this direction, we introduce a practical, computational framework that enables socially aware inference. We demonstrate the framework's ability to model a common, complex, and under-investigated aspect of human social behavior: deception. Moreover, we show how a system implementing this framework could dynamically respond once it has detected a lie. We then discuss some of the challenges associated with deception, ending with an outline of future research directions.

Evidence-based reasoning is at the core of many problem solving and decision making tasks in a wide variety of domains. This paper introduces a computational theory of evidence-based reasoning, the architecture of a learning agent shell which incorporates general knowledge for evidence-based reasoning, a methodology that uses the shell to rapidly develop cognitive assistants in a specific domain, and a sample cognitive assistant for intelligence analysis.

In the context of cognitive architectures, memory is typically considered as a passive storage device with the sole purpose of maintaining and retrieving information relevant to ongoing cognitive processing. If memory is instead considered to be a fundamentally active aspect of cognition, as increasingly suggested by empirically-derived neurophysiological theory, this passive role must be reinterpreted. In this perspective, memory is the distributed substrate of cognition, forming the foundation for cross-modal priming, and hence soft cross-modal coordination. This paper seeks to describe what a cognitive architecture based on this perspective must involve, and initiates an exploration into how human-level cognitive competencies (namely episodic memory, word label conjunction learning, and social behaviour) can be accounted for in such a low-level framework. This proposal of a memory-centred cognitive architecture presents new insights into the nature of cognition, with benefits for computational implementations such as generality and robustness that have only begun to be exploited.

Recommender systems now play an important role in online information discovery, complementing traditional approaches such as search and navigation, with a more proactive approach to discovery that is informed by the users interests and preferences. To date recommender systems have been deployed within a variety of e-commerce domains, covering a range of products such as books, music, movies, and have proven to be a successful way to convert browsers into buyers. Recommendation technologies have a potentially much greater role to play in information discovery however and in this article we consider recent research that takes a fresh look at web search as a fertile platform for recommender systems research as users demand a new generation of search engines that are less susceptible to manipulation and more responsive to searcher needs and preferences.

The Association for the Advancement of Artificial Intelligence, in cooperation with Stanford University's Department of Computer Science, presented the 2011 Spring Symposium Series Monday through Wednesday, March 21–23, 2011 at Stanford University. The titles of the eight symposia were AI and Health Communication, Artificial Intelligence and Sustainable Design, AI for Business Agility, Computational Physiology, Help Me Help You: Bridging the Gaps in Human-Agent Collaboration, Logical Formalizations of Commonsense Reasoning, Multirobot Systems and Physical Data Structures, and Modeling Complex Adaptive Systems As If They Were Voting Processes.

The 19th robotics program at the annual AAAI conference was held in Atlanta, Georgia in July 2010. In this article we give a summary of three components of the exhibition: small scale manipulation challenge: robotic chess; the learning by demonstration challenge, and the education track. We also describe the participating teams, highlight the research questions they tackled and briefly describe the systems they demonstrated.