09:00-10:00: Invited Talk
9:00am: A Tutorial on Constraint Acquisition.
Dimos Tsouros
Abstract:
Constraint Programming (CP) is a powerful paradigm for solving complex combinatorial problems, but its adoption is often hindered by the expertise required for modeling. Constraint Acquisition (CA) aims to mitigate this bottleneck by semi-automating the modeling process, exploiting machine learning methods. This tutorial will provide an introduction to CA, covering both passive and interactive learning approaches, highlighting the recent integration of statistical Machine Learning methods that enhance robustness and efficiency. During the tutorial, state-of-the-art interactive CA methods implemented in the open source PyConA python library will be demonstrated. Finally, we will discuss current challenges and future directions in constraint acquisition research.
10:00am:
A CPMpy-based Python Library for Constraint Acquisition - PYCONA.
Dimos Tsouros, Tias Guns
10:30-11:00: Break (Light refreshments available near session rooms)
11:00-12:30: CSP/LLM
A Neurosymbolic Fast and Slow Architecture for Graph Coloring
Vedant Khandelwal, Vishal Pallagani, Biplav Srivastava, Francesca Rossi
Combining Constraint Programming Reasoning with Large Language Model Predictions
Florian Régin, Elisabetta De Maria, Alexandre Bonlarron
Exploiting Large Language Models for the Automated Generation of Constraint Satisfaction Problems
Lothar Hotz, Christian Bähnisch, Sebastian Lubos, Alexander Felfernig, Albert Haag, Johannes Twiefel
[
Slides
]
Constraint Modelling with LLMs Using In-Context Learning
Kostis Michailidis, Dimos Tsouros, Tias Guns
Generating Streamlining Constraints with Large Language Models
Florentina Voboril, Vaidyanathan Peruvemba Ramaswamy, Stefan Szeider
MCP-Solver: Integrating Language Models with Constraint Programming Systems
Stefan Szeider
12:30-14:00: Lunch
14:00-15:00: Pot Pourri
Neuro-Symbolic Action Anticipation with Learned Constraints
Muyang Yan, Maxwell J. Jacobson, Simon Stepputtis, Katia Sycara, Yexiang Xue
Fuzzy Logic Acquisition with Multi-modal Contexts
Maxwell J. Jacobson, Yexiang Xue
Learning Markov Random Fields for Combinatorial Structures via Sampling through Lovász Local Lemma
Nan Jiang, Yi Gu, Yexiang Xue
Extracting Problem Structure with LLMs for Optimized SAT Local Search
André Schilder, Stefan Szeider
15:00-15:30: Software
Advancing Decision Science: Lessons from the Machine Learning Community
Serdar Kadioglu
