Metraipolis › archive › dc_3ff8426e2e75

Learning Symbolic Constraint Representations from Examples: A Neuro-Symbolic Approach — arXiv:2609.12267

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12267
License (as archived)
CC0-1.0
Archived
2026-10-16T03:02:36.846Z
SHA-256 of the archived text
8ae4aacc892c3528a6b556093df9dea0a52c2953f5b29bfa521bcba760993732
Stable URL of this page
https://metraipolis.com/documento/dc_3ff8426e2e75

How to cite

Learning Symbolic Constraint Representations from Examples: A Neuro-Symbolic Approach — arXiv:2609.12267 — arXiv (en), https://arxiv.org/abs/2609.12267 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ff8426e2e75 (Metraipolis archive dc_3ff8426e2e75, sha256 8ae4aacc892c3528a6b556093df9dea0a52c2953f5b29bfa521bcba760993732)
BibTeX
@misc{dc3ff8426e2e75,
  title = {Learning Symbolic Constraint Representations from Examples: A Neuro-Symbolic Approach — arXiv:2609.12267},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12267},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ff8426e2e75; sha256 8ae4aacc892c3528a6b556093df9dea0a52c2953f5b29bfa521bcba760993732},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12267. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning user-defined concepts as constraint networks has been extensively studied in the constraint acquisition (CA) literature. However, existing approaches typically rely on intensive interactions with a human oracle, making the learning process costly in terms of time and number of queries. In this paper, we propose a neuro-symbolic framework for automatic CA that significantly reduces user involvement by introducing neural Oracle Transformer models which learn to emulate user responses and to generalize conceptual knowledge. Trained on previously available examples, the learned oracle interacts with a dedicated CA engine, FastCA, which systematically refines the oracle's responses into a sound, consistent, and interpretable constraint network. This neuro-symbolic interaction enables the recovery of structured symbolic models from data without prior domain knowledge. Our results demonstrate that this neuro-symbolic interplay effectively aligns data-driven pattern recognition with symbolic reasoning, offering a robust approach to automating model construction in combinatorial domains.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.12267 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T02:51:27.767Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).