We describe a virtual member of a knowledge management Community of Practice (CoP), called ATHENA, that knows an individual, his tasks, his organization, and the community. ATHENA employs an agentic chat capability that combines embeddings with knowledge-based faceted search to provide accurate responses to technical questions along with rationale and citations for efficient validation. ATHENA supports natural, in-the-flow capture of task-related insights to share within a CoP, along with proactive dissemination of information tied to an individual and his current needs. An evaluation involving 75 professionals from the Oil & Gas sector shows that ATHENA dramatically improved outcomes and productivity on a set of well-planning tasks compared to their use of a state-of-the-art RAG baseline. Interestingly, ATHENA also enabled eight non-experts to perform at expert levels.

This paper describes the genetic algorithm used to select news stories about artificial intelligence for AAAI’s weekly AIAlert, emailed to nearly 11,000 subscribers. Each week, about 1,500 news stories covering various aspects of artificial intelligence and machine learning are discovered by i2k Connect’s NewsFinder agent. Our challenge is to select just 10 stories from this collection that represent the important news about AI. Since stories and topics do not necessarily repeat in later weeks, we cannot use click tracking and supervised learning to predict which stories or topics are most preferred by readers. Instead, we must build a representative selection of stories a priori, using information about each story’s topics, content, publisher, date of publication, and other features. This paper describes a genetic algorithm that achieves this task. We demonstrate its effectiveness by comparing several engagement metrics from six months of “A/B testing” experiments that compare random story selection vs. a simple scoring algorithm vs. our new genetic algorithm.

Both industry and academia are confronting the challenge of big data, i.e., data processing that involves data so voluminous or arriving at such high velocity that no single commodity machine is capable of storing or processing them all. A common approach to handling big data is to divide and distribute the processing job to a cluster of machines. Ideally, a course that teaches students how to work with big data would provide students access to a cluster for hands-on practice. However, a cluster of physical, on-premise machines may be prohibitively expensive, particularly at smaller institutions with smaller budgets.

My research seeks to answer the question of how any agent that is tasked with making sense of its world, by finding explanations for evidence (e.g., sensor reports) using domain-general strategies, may accurately and efficiently handle incomplete evidence, noisy evidence, and an incomplete knowledge base. I propose the following answer to the question. The agent should employ an optimal abductive reasoning algorithm (developed piece-wise and shown to be best in a class of similar algorithms) that allows it to reason from evidence to causes. For the sake of efficiency and operational concerns, the agent should establish beliefs periodically rather than waiting until it has obtained all evidence it will ever be able to obtain. If the agent commits to beliefs on the basis of incomplete or noisy evidence or an incomplete knowledge base, these beliefs may be incorrect. Future evidence obtained by the agent may result in failed predictions or anomalies. The agent is then tasked with determining whether it should retain its beliefs and therefore discount the newly-obtained evidence, revise its prior beliefs, or expand its knowledge base (what can be described as anomaly-driven or explanation-based learning). I have developed an abductive metareasoning procedure that aims to appropriately reason about these situations. Preliminary experiments in two reasoning tasks indicate that the procedure is effective.