Herb.jl: A Unifying Program Synthesis Library
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915763208585216 |
|---|---|
| author | Hinnerichs, Tilman Reid, Reuben Gardos de Jong, Jaap Swinkels, Bart Wochner, Pamela Filat, Nicolae Magurescu, Tudor Hanou, Issa Dumancic, Sebastijan |
| author_facet | Hinnerichs, Tilman Reid, Reuben Gardos de Jong, Jaap Swinkels, Bart Wochner, Pamela Filat, Nicolae Magurescu, Tudor Hanou, Issa Dumancic, Sebastijan |
| contents | Program synthesis -- the automatic generation of code given a specification -- is one of the most fundamental tasks in artificial intelligence (AI) and the dream of many programmers. Numerous synthesizers have been developed for program synthesis, offering different approaches to the exponentially growing program space. Although such state-of-the-art tools exist, reusing and adapting them remains tedious and time-consuming. We propose Herb.jl, a unifying program synthesis library written in Julia, to address these issues. Since current methods share similar building blocks, we aim to break down the underlying algorithms into extendable, reusable subcomponents. To demonstrate the benefits of using Herb.jl, we show how to implement a simple problem and grammar, and how to solve it with just a few lines of code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09726 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Herb.jl: A Unifying Program Synthesis Library Hinnerichs, Tilman Reid, Reuben Gardos de Jong, Jaap Swinkels, Bart Wochner, Pamela Filat, Nicolae Magurescu, Tudor Hanou, Issa Dumancic, Sebastijan Programming Languages Artificial Intelligence Software Engineering Program synthesis -- the automatic generation of code given a specification -- is one of the most fundamental tasks in artificial intelligence (AI) and the dream of many programmers. Numerous synthesizers have been developed for program synthesis, offering different approaches to the exponentially growing program space. Although such state-of-the-art tools exist, reusing and adapting them remains tedious and time-consuming. We propose Herb.jl, a unifying program synthesis library written in Julia, to address these issues. Since current methods share similar building blocks, we aim to break down the underlying algorithms into extendable, reusable subcomponents. To demonstrate the benefits of using Herb.jl, we show how to implement a simple problem and grammar, and how to solve it with just a few lines of code. |
| title | Herb.jl: A Unifying Program Synthesis Library |
| topic | Programming Languages Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2510.09726 |