Vol-4229
urn:nbn:de:0074-4229-x

Copyright © 2026 for the individual papers by the papers' authors. Copyright © 2026 for the volume as a collection by its editors. This volume and its papers are published under the Creative Commons License Attribution 4.0 International (CC BY 4.0).

SKILLED-LLMs 2026
Statistics and Knowledge Integration for Logic, Learning, Ethical Decisions, and LLMs 2026

Proceedings of the Joint Workshop on Statistics and Knowledge Integration for Logic, Learning, Ethical Decisions, and LLMs (SKILLED-LLMs 2026)
co-located with the Federated Logic Conference 2026 (FLoC 2026)

Lisbon, Portugal, July 18, 2026.

Edited by

Ha Thanh Nguyen ¹
Francesca Toni ²
Kostas Stathis ³
Ken Satoh ⁴
Randy Goebel ⁵
Francesco Chiariello ⁶
Yves Lesperance 7
Matteo Magnini ⁸
Federico Sabbatini ⁹
Elena Umili ¹⁰
Nourhan Ehab ¹¹
Mervat AbuElkheir ¹¹

¹ NII, Tokyo, Japan
² Imperial College London, UK
³ Royal Holloway University of London, UK
⁴ ROIS-DS, Tokyo, Japan
⁵ University of Alberta, Canada
⁶ Inria & ENS | PSL, France
⁷ York University, Canada
⁸ University of Luxembourg, Luxembourg
⁹ University of Bologna, Italy
¹⁰ Sapienza University of Rome, Italy
¹¹ German University in Cairo, Egypt

Table of Contents

Preface
Summary: There were 19 papers submitted for peer-review to this workshop. Out of these, 16 papers were accepted for this volume.

Regular Papers

First Steps Towards Human-AI Ranking Aggregation 1–14
Jonas Karge, Roy Ferguson, Daniel Grimaldi, Jonas Haldimann, Ruvarashe Madzime, Thomas Meyer
Neurosymbolic Clinical Reasoning: From Evidence Extraction to Reason-Based Decision 15–22
Henrique Marcos, Foivos Ioannis Tzavellos, Rohan Nanda
Neuro-Symbolic Injection of LTLf Constraints in Autoregressive Reinforcement Learning Policies 23–38
Ashkan Ansarifard, Matteo Mancanelli, Elena Umili, Fabio Patrizi
KGP-QG: Multi-hop Reasoning with Knowledge Graphs in LLMs 39–50
Al Hasib Mahamud, Yllias Chali
Automatic Chain of Concepts: Conceptual Prompting for LLMs by Constructing Concept Trees 51–73
Hurile Borjigin, Nishtha N. Vaidya, Thomas A. Runkler, Veronika Haderlein-Høgberg
Deep Weighted Finite Automata 74–87
Francesco Casone, Rafael Peñaloza
PrologMCP: A Standardized Prolog Tool Interface for LLM Agents 88–110
Agnieszka Mensfelt, Adarsh Prabhakaran, Adrian Haret, Vince Trencsenyi, Kostas Stathis
A Parametric Model of Cognitive Complexity for Symbolic Knowledge-Based Decision Systems 111–125
Federico Sabbatini
NL2UNIFOL: from Natural Language Sentences to Uniform First-Order Logic Formulae 126–143
Matteo Magnini, Davide Liga, Luca Pasetto
A Semantic Knowledge Graph Construction Pipeline for Vehicle Intention Prediction in nuScenes 144–154
Khaled Nowara, Mohamed Manzour, Catherine Elias
Epistemically-Constrained Belief Harmonization: Integrating Symbolic Structure with Probabilistic Consensus 155–163
Adam Kostka, Jarosław A. Chudziak
On the Reliability of LLM Orchestration Under Horizontal Knowledge Partitioning 164–178
Mayar Osama, Nourhan Ehab, Mervat AbuElkheir

Short Papers

Toward a Requirements-Driven Neuro-Symbolic Approach to Developing Trustworthy AI Agent Systems 179–186
Bita Banihashemi, Yves Lespérance, Sotirios Liaskos
Enhancing Retrieval-Augmented Generators with Symbolic Query Definitions 187–200
Filippo Bianchini, Marco Calamo, Marco Console, Massimo Mecella, Laura Papi
When AI Should Refuse to Decide: Formal Irresolution and the Ethics of Legal Indeterminacy in LLM-Based Reasoning for Biodiversity Law 201–207
Rohan Nanda, Henrique Marcos, Julia Schutz Veiga
Identifying Semantic Gaps between Legal Case Descriptions and Logical Fact Formulas Using LLMs: Definition and Preliminary Evaluation 208–212
Wachara Fungwacharakorn, May Myo Zin, Ken Satoh

2026-07-15: submitted by Federico Sabbatini, metadata incl. bibliographic data published under Creative Commons CC0
2026-07-23: published on CEUR Workshop Proceedings (CEUR-WS.org, ISSN 1613-0073) |valid HTML5|