Celeste Veronese and Daniele Meli are pleased to announce the Workshop on Neuro‑Symbolic Intelligence for LLMs and Autonomous Agents, which will take place at IJCAI‑ECAI 2026 in Bremen, Germany. Co-organized with Alessandra Russo (Imperial College London), Abulhair Saparov (Purdue University), Djallel Bouneffouf (IBM) and Pranava Madhyastha (City St. George University London), the workshop brings together researchers from academia and industry to explore how neurosymbolic AI can advance the next generation of large language models and autonomous agents. By fostering dialogue across communities working on reasoning, learning, planning, and interaction, the event aims to consolidate emerging ideas and shape the future of hybrid intelligent systems. The workshop welcomes contributions that investigate how symbolic structures and sub‑symbolic models can be combined to support more capable, explainable, and trustworthy agents. Topics of interest include neurosymbolic approaches for autonomous and multi‑agent systems, the integration of LLMs with reasoning and planning, the development of world models and symbolic action representations, and methods for learning abstractions from raw data. We are also interested in work addressing interpretability, verification, hybrid architectures for perception and action, human‑in‑the‑loop knowledge integration, and the design of benchmarks and real‑world evaluations.
This tutorial by Celeste Veronese and Daniele Meli provides a theoretical and practical introduction to Neurosymbolic decision making, with a particular focus on Reinforcement Learning (NeSyRL) for autonomous agents. This emerging paradigm combines the strengths of symbolic reasoning (expressive abstraction and generalization) with the adaptability of Deep RL under uncertainty. Participants will explore how symbolic task knowledge can be represented in various ways, from reward machines to structured logic programs, enabling declarative representations of actions, constraints, and preferences for decision making. The core of the tutorial presents a critical overview of leading NeSyRL frameworks that integrate these symbolic abstractions into RL algorithms, producing autonomous agents that balance interpretability, safe generalization, and data efficiency. Practical examples from both single- and multi-agent scenarios will complement the theoretical discussion, equipping attendees with methods and tools for neurosymbolic decision making. Finally, the tutorial will highlight current trends and open challenges that are shaping the future of this rapidly evolving research field.
In the spirit of the Italian National Digital School Plan, the Department of Computer Science of the University of Verona, Sapienza University and International Study University of Rome promote and showcase the use of Robotics and Artificial Intelligence in various contexts of high social value.