ReSyn: A Generalized Recursive Regular Expression Synthesis Framework

2026-03-24

AI Summary

This work addresses the significant performance degradation of existing Programming-by-Example (PBE) systems when synthesizing real-world regular expressions characterized by high structural complexity, such as deep nesting and frequent unions. To overcome this limitation, the authors propose ReSyn—a general, synthesizer-agnostic recursive divide-and-conquer framework that decomposes complex synthesis tasks into manageable subproblems. Complementing this framework, they introduce Set2Regex, a parameter-efficient neural synthesizer that explicitly models the permutation invariance of input examples. The combined approach substantially improves the accuracy of diverse synthesizers on challenging regular expression synthesis tasks, achieving a new state-of-the-art result on a difficult benchmark.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Search and Optimization: Mixed Discrete/Continuous Search
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Existing Programming-By-Example (PBE) systems often rely on simplified benchmarks that fail to capture the high structural complexity-such as deeper nesting and frequent Unions-of real-world regexes. To overcome the resulting performance drop, we propose ReSyn, a synthesizer-agnostic divide-and-conquer framework that decomposes complex synthesis problems 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.

Problem

• regular expression synthesis
• Programming-by-Example
• structural complexity
• nested regexes
• Unions

Innovation

• Recursive Regular Expression Synthesis
• Programming-by-Example
• Divide-and-Conquer Framework
• Permutation Invariance
• Set2Regex