LLMs meet Constraint Solving
CP/SAT 2025 Workshop
Monday August 11, 2025
Glasgow, Scotland
CP/SAT 2025 Workshop
Monday August 11, 2025
Glasgow, Scotland
Submission deadline: June 06, 2025
Notification: June 25, 2025
Workshop date: August 11, 2025
Large Language Models (LLMs) have shown remarkable capabilities in natural language processing, opening exciting opportunities in many domains and applications, like chatbots and code generation. However, their reliance on statistical patterns makes them prone to errors, hallucinations, and a lack of formal guarantees—hindering their application in domains requiring structured reasoning and reliability.
On the other hand, constraint-solving technologies such as CP/SAT/OR provide a framework for modeling and solving combinatorial problems with provable guarantees on correctness, optimality, and explainability. Yet, the need for expert knowledge in formalizing problems and selecting appropriate solving techniques often limits the wider adoption of such technologies.
By combining the strengths of LLMs and constraint solving, new opportunities arise: LLMs can assist in model formulation, constraint acquisition, and interactive solving, while constraint solvers can provide formal verification, control mechanisms, and structured reasoning for LLMs. Recent research has already shown promising results in both directions, from LLM-assisted constraint modeling to using CP/SAT/OR solvers for guiding and validating LLM outputs.
The LLM-Solve workshop aims to bring together researchers working at this exciting frontier to discuss challenges, synergies, and future research directions. This workshop aims to shape the future of LLM-powered constraint solving and constraint-driven LLMs.
The LLM-Solve 2025 workshop aims to bring together researchers exploring the intersection of Large Language Models (LLMs) and Constraint Solving (CP, SAT, SMT, MIP, and related paradigms). This workshop provides a platform to discuss recent advances, challenges, and opportunities in combining LLMs and constraint solving.
The workshop covers both directions of this interaction:
LLMs for Constraint Solving: Investigating how LLMs can be used to tackle challenges in constraint solving research, i.e., assist in constraint modeling, solving, and explanations; including automated constraint acquisition, solver configuration and selection, solver heuristics, automated solver code generation and natural-language based solving and solution refinement.
Constraint Solving for LLMs: Exploring how constraint-solving techniques can improve LLM reasoning and verification, LLM safety, and applications in structure reasoning, formal verification, and more.
The topics of interest include (but are not restricted to):
LLMs for constraint modeling and acquisition
LLM-guided solver heuristics and search strategies
Hybrid approaches combining LLMs and constraint solvers
Constraint solvers for improving LLM reasoning and verification
SAT/CP-based methods for controlling or guiding LLM outputs
LLM-driven explanations and interactive constraint solving
Benchmarks, datasets and evaluation methodologies for LLM-Constraint integration
Real-world applications involving the use of constraint-solving technologies and LLMs.
This workshop welcomes contributions from both theoretical and applied perspectives, fostering discussions between researchers in CP, SAT, AI, OR, and NLP who are interested in bridging the gap between constraint solving and natural language processing with LLMs.
Authors are invited to send contributions in the form of extended abstracts (maximum 2 pages, without including the references). The authors can optionally add up to 10 pages of technical report after the extended abstract. Submissions can be published journal/conference papers, original work, work in progress with preliminary results, or position papers.
Contributions should be submitted in the form of a PDF file, following LIPIcs guidelines: https://submission.dagstuhl.de/series/details/5#author)
The workshop co-chairs will select the papers to be presented at the workshop according to their suitability to the aims. All presenters and attendees are expected to register to the CP/SAT workshop day.
Submission web page: https://openreview.net/group?id=a4cp.org/CP/2025/Workshop/LLM-Solve
The workshop co-chairs are:
Tias Guns (KU Leuven, Belgium), https://people.cs.kuleuven.be/~tias.guns/
Serdar Kadıoglu (Brown University, USA), https://skadio.github.io/
Stefan Szeider (TU Wien, Austria), https://www.ac.tuwien.ac.at/people/szeider/
Dimos Tsouros (KU Leuven, Belgium), https://dimostsouros.github.io/