Integrating multiple reasoning mode is useful in complex domains like the game of Go. Go players use various forms of reasoning during a game. Reasoning at the tactical level is completely different from reasoning at the strategic level. Choosing a plan requires a different form of reasoning than knowing how to execute a plan. This paper gives examples of the integration of these reasoning modes into a single system. Rule-based reasoning, Constraint-based reasoning and Case-based reasoning are used in this hierarchical order. Constraint-based reasoning uses the results of Rule-based reasoning, and Case-based reasoning uses the results of Constraint-based reasoning and Rule-based reasoning. Introduction Integrating multiple reasoning modes is useful in complex domains like the game of Go. Go players use various types of reasoning during a game. Reasoning at the tactical level is completely different from reasoning at the strategic level. Choosing a plan requires a differen...

In this paper a functionality taxonomy for document search engines is proposed. It can be used to assess the features of a search engine, to position search engines relative to each other, or to select which search engine `fits' a certain situation. One is able to identify areas for improvement. During development, we were guided by the viewpoint of the user. We use the word `search engine' in the broadest sense possible, including library and web based (meta) search engines.

Goal Driven Learning (GDL) focuses on systems that determine by themselves what has to be learnt and how to learn it. Typically GDL systems use meta-reasoning capabilities over a base reasoner, identifying learning goals and devising strategies. In this paper we present a novel GDL technique to deal with complex AI systems where the metareasoning module has to analyze the reasoning trace of multiple components with potentially different learning paradigms. Our approach works by distributing the generation of learning strategies among the different modules instead of centralizing it in the meta-reasoner. We implemented our technique in the GILA system, that works in the airspace task orders domain, showing an increase in performance. 1

Developing systems that learn how to perform complex tasks presents a significant challenge to the artificial intelligence community. As the knowledge to be learned becomes complex, with diverse procedural constructs and uncertainties to be validated, the system needs to integrate a wide range of learning and reasoning methods with different focuses and strengths. For example, one learning method may be used to generalize from user demonstrations, another to learn by practice and exploration, and another to test hypotheses with experiments. The POIROT system pursues such a multistrategy learning methodology that employs multiple integrated learners and knowledge validation modules to acquire complex process knowledge for a medical logistics domain (Burstein et al., 2008). For a learning system of such complexity, activities of participating agents must be coordinated to ensure that their collective activities produce the desired procedural knowledge. This kind of control is inherently metalevel (Anderson & Oates, 2007; Cox & Raja, Chapter 1) in that it requires the system to reflect on