Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.07867 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912579059712000 |
|---|---|
| author | Crespin, Augustin Kostis, Ioannis Verhaeghe, Hélène Schaus, Pierre |
| author_facet | Crespin, Augustin Kostis, Ioannis Verhaeghe, Hélène Schaus, Pierre |
| contents | Constraint Programming and its high-level modeling languages have long been recognized for their potential to achieve the holy grail of problem-solving. However, the complexity of modeling languages, the large number of global constraints, and the art of creating good models have often hindered non-experts from choosing CP to solve their combinatorial problems. While generating an expert-level model from a natural-language description of a problem would be the dream, we are not yet there. We propose a tutoring system called CP-Model-Zoo, exploiting expert-written models accumulated through the years. CP-Model-Zoo retrieves the closest source code model from a database based on a user's natural language description of a combinatorial problem. It ensures that expert-validated models are presented to the user while eliminating the need for human data labeling. Our experiments show excellent accuracy in retrieving the correct model based on a user-input description of a problem simulated with different levels of expertise. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_07867 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CP-Model-Zoo: A Natural Language Query System for Constraint Programming Models Crespin, Augustin Kostis, Ioannis Verhaeghe, Hélène Schaus, Pierre Artificial Intelligence Constraint Programming and its high-level modeling languages have long been recognized for their potential to achieve the holy grail of problem-solving. However, the complexity of modeling languages, the large number of global constraints, and the art of creating good models have often hindered non-experts from choosing CP to solve their combinatorial problems. While generating an expert-level model from a natural-language description of a problem would be the dream, we are not yet there. We propose a tutoring system called CP-Model-Zoo, exploiting expert-written models accumulated through the years. CP-Model-Zoo retrieves the closest source code model from a database based on a user's natural language description of a combinatorial problem. It ensures that expert-validated models are presented to the user while eliminating the need for human data labeling. Our experiments show excellent accuracy in retrieving the correct model based on a user-input description of a problem simulated with different levels of expertise. |
| title | CP-Model-Zoo: A Natural Language Query System for Constraint Programming Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.07867 |