Abstract: Neurosymbolic learning (NSL)—the integration of neural and symbolic mechanisms for inference and learning—has been proposed as a remedy for some of the most critical limitations of neural networks. A problem that has received considerable attention in the relevant literature is that of weakly supervised learning in the presence of a symbolic component. In this problem, one or more neural classifiers perform symbolic grounding, mapping low-level inputs onto high-level symbolic concepts. A symbolic component then infers outputs consistent with both the predicted concepts and any provided prior knowledge, and learning is driven by supervision applied only to the outputs of the symbolic component. Research has uncovered an intriguing pitfall. In particular, symbol grounding can "deceive" the learning process: even when the neural classifiers produce incorrectly grounded concepts, the symbolic component may still infer outputs that match the ground truth. 

This talk provides an overview of research on weakly supervised NSL over the last eight years, with a focus on the above challenge. We begin by discussing early learning frameworks, then present the main theoretical results—including PAC-learnability, reasoning shortcuts, and learning imbalances. We conclude with an overview of strategies for improving learning efficiency, delving into a specific technique that enhances the accuracy of learned classifiers by up to 53% through better exploiting the representation space.

Abstract: LLM agents are powerful, but they still struggle with reliable reasoning, planning, and consistency in real-world workflows. This talk explores how neuro-symbolic AI can improve agent reliability by combining neural models with symbolic reasoning, verification, structured memory, and tool-based execution. The presentation will cover emerging architectures for multi-step reasoning agents, practical enterprise challenges, and directions toward more trustworthy and explainable AI systems.

Bio: Dr. Asim Munawar is a Project Lead at IBM’s Watson Research Center in New York, where he heads efforts to enhance reasoning, planning, and agentic workflows in enterprise-scale large language models. With over 15 years of experience in AI—more than a decade of it at IBM Research—he has held key leadership roles, including Manager and Program Director for Neuro-Symbolic AI. Dr. Munawar earned his Ph.D. from Hokkaido University, Japan, and has authored over 80 peer-reviewed publications. He is an inventor on 20+ U.S. patents and a frequent keynote and invited speaker at top venues such as IJCAI, ICSE, and ACMSE. He also serves on advisory boards for the National Center of Artificial Intelligence in Pakistan and the Centaur AI Institute in the U.S. His work focuses on building scalable, high-impact AI systems and fostering strong, diverse teams. He continues to advance the capabilities of AI for solving real-world enterprise challenges.

Abstract: AI systems increasingly need to learn to reason rigorously. From early symbolic logic through the deep learning era to today's LLMs, reasoning is the key component of AI technologies. Neurosymbolic AI meets this need by embedding or combining formalized reasoning into learning systems. Recent deployments in industry show that neurosymbolic methodologies are increasingly more relevant. This talk presents RAIL (Reasoning, Assurances, Interfacing, Learning), a framework proposed by a group of experienced neurosymbolic AI researchers from academia and industry offering four qualitative spectra for characterizing any neurosymbolic system. Applied across six domains, RAIL shows that many high-impact AI systems are already neurosymbolic, whether or not they're built that way by design.

Abstract: This talk presents a unified formal perspective on neurosymbolic methods, which combine learning and reasoning in AI, showing how many seemingly different approaches can be understood through the lens of deep probabilistic logics. It further illustrates how this perspective can provide a foundational semantic substrate for emulating existing approaches and developing the next generation of neurosymbolic methods.

Bio: Giuseppe Marra is an Assistant Professor in the Declarative Languages and Artificial Intelligence (DTAI) research group at KU Leuven, where he co-leads the DeepLog team. His research focuses on the integration of neural computation and symbolic reasoning, with an emphasis on logical and probabilistic methods for neurosymbolic AI. He has contributed to several prototypical neurosymbolic frameworks and works on foundations and applications of neurosymbolic learning in areas such as concept based interpretable deep models and safe reinforcement learning.