This volume contains the revised versions of the 8 regular, short and position papers presented at the First Workshop on: \Deep Understanding and Reasoning: A Challenge for Next-generation Intelligent Agents (URANIA)". The workshop was held in Genova, Italy, on the 28th of November 2016, in the context of the 15th International Conference of the Italian Association for Arti cial Intelligence (AI*IA 2016).
The aim of the workshop was to bring together Arti cial Intelligence (AI) researchers with complementary skills and background and to foster a discussion aimed at cross-fertilizing di erent AI sectors and to provide concrete means for autonomous reasoning agents design and evaluation. In a computer-aided problem solving process, there is always a substantial human intervention enabling the encoding of a problem in a machine-understandable model, which in turn can be solved automatically through a problem solving technique/algorithm. The human intervention is essential for identifying problem components, common-sense and hid-den knowledge in the problem description and to nally craft a computable model.
In a long-term vision, next-generation arti cial intelligent systems and robots will be autonomous end-to-end solvers that perform the whole problem-solving process without any human intervention. Starting from a (possibly multi-modal) problem description, an end-to-end problem solver should automatically understand the problem, identify its components, devise a model, select a solving technique, and nd a solution. Such autonomous intelligent agents should be pro-active and problem-solving driven; deep understanding and deep reasoning, not necessarily based on big-data, will be a crucial ingredient for their design.
In this context, it would be important to identify speci c challenges, to assess the level of autonomy achieved, the e ectiveness of end-to-end solvers, and to ease the dissemination of AI results to a general audience. This ambitious goal requires an unprecedented integration of AI areas and could represent an important step forward reducing the fragmentation of modern AI. Therefore, works and challenges presented at the workshop demand a combined e ort of integration of di erent AI techniques such as Natural Language Processing, Machine Learning, Constraint-based reasoning, Logic and Automated Reasoning, Common-sense Reasoning, Human-Machine Interaction and Cognitive Science. We would like to thank all authors for their contributions, the members of the program committee for their valuable work in reviewing the papers, Claudia Schon (Universitat Koblenz-Landau) for her very relevant invited talk \Commonsense Reasoning meets Theorem Proving" and Luigia Carlucci Aiello for the interesting concluding remarks. We are also grateful to the Italian Association for Arti cial Intelligence (AI*IA), the local organizers in Genova, and the Department of Computer Science and Engineering of the University of Bologna (DISI) for their help, support and sponsorship.
Organization
Marco Gori, Universita di Firenze Evelina Lamma, Universita di Ferrara Bernardo Magnini, FBK-Trento Daniele Nardi, Universita di Roma La Sapienza Andrea Omicini, Universita di Bologna Piero Poccianti, Gruppo Operativo MPS di Firenze Fabrizio Riguzzi, Universita di Ferrara Francesca Rossi, Universita di Padova Giovanni Semeraro, Universita di Bari Paolo Torroni, Universita di Bologna