English

An Agentic Framework for Neuro-Symbolic Programming

Artificial Intelligence 2026-01-05 v1

Abstract

Integrating symbolic constraints into deep learning models could make them more robust, interpretable, and data-efficient. Still, it remains a time-consuming and challenging task. Existing frameworks like DomiKnowS help this integration by providing a high-level declarative programming interface, but they still assume the user is proficient with the library's specific syntax. We propose AgenticDomiKnowS (ADS) to eliminate this dependency. ADS translates free-form task descriptions into a complete DomiKnowS program using an agentic workflow that creates and tests each DomiKnowS component separately. The workflow supports optional human-in-the-loop intervention, enabling users familiar with DomiKnowS to refine intermediate outputs. We show how ADS enables experienced DomiKnowS users and non-users to rapidly construct neuro-symbolic programs, reducing development time from hours to 10-15 minutes.

Keywords

Cite

@article{arxiv.2601.00743,
  title  = {An Agentic Framework for Neuro-Symbolic Programming},
  author = {Aliakbar Nafar and Chetan Chigurupati and Danial Kamali and Hamid Karimian and Parisa Kordjamshidi},
  journal= {arXiv preprint arXiv:2601.00743},
  year   = {2026}
}
R2 v1 2026-07-01T08:48:38.351Z