| title | ReSyn: A Generalized Recursive Regular Expression Synthesis Framework |
|---|---|
| authors | Seongmin Kim, Hyunjoon Cheon, Su-Hyeon Kim, Yo-Sub Han, Sang-Ki Ko |
| date | 2026-06-13 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2603.24624 |
| upvotes | 2 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Existing Programming-By-Example (PBE) systems often rely on simplified benchmarks that fail to capture the high structural complexity of real-world regexes, such as deeper nesting and frequent use of union operations. To overcome the resulting performance drop, we propose ReSyn, a synthesizer-agnostic divide-and-conquer framework that decomposes complex synthesis problem into manageable sub-problems. We also introduce Set2Regex, a parameter-efficient synthesizer capturing the permutation invariance of examples. Experimental results demonstrate that ReSyn significantly boosts accuracy across various synthesizers, and its combination with Set2Regex establishes a new state-of-the-art on challenging real-world benchmark. The complete source code, datasets, and pre-trained model checkpoints are publicly available at https://github.com/mrseongminkim/ReSyn. |
cite
@misc{kim2026resyn,
title={ReSyn: A Generalized Recursive Regular Expression Synthesis Framework},
author={Seongmin Kim and Hyunjoon Cheon and Su-Hyeon Kim and Yo-Sub Han and Sang-Ki Ko},
year={2026},
eprint={2603.24624},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2603.24624}
}