# Learning Symbolic Constraint Representations from Examples: A Neuro-Symbolic Approach

arXiv: https://arxiv.org/abs/2609.12267 · HTML: https://mlsanity.com/paper/2609.12267/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 17 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 4 of 4)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Can Transformers Reason Logically? A Study in SAT Solving](https://mlsanity.com/paper/2410.07432/) (2024)
- [Efficient Multiple Constraint Acquisition](https://mlsanity.com/paper/2109.05920/) (2021)
- [Guided Bottom-Up Interactive Constraint Acquisition](https://mlsanity.com/paper/2307.06126/) (2023)

## Abstract (arXiv)

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.