An Agentic Framework for Neuro-Symbolic Programming
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909980022538240 |
|---|---|
| author | Nafar, Aliakbar Chigurupati, Chetan Kamali, Danial Karimian, Hamid Kordjamshidi, Parisa |
| author_facet | Nafar, Aliakbar Chigurupati, Chetan Kamali, Danial Karimian, Hamid Kordjamshidi, Parisa |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_00743 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | An Agentic Framework for Neuro-Symbolic Programming Nafar, Aliakbar Chigurupati, Chetan Kamali, Danial Karimian, Hamid Kordjamshidi, Parisa Artificial Intelligence I.2.7 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. |
| title | An Agentic Framework for Neuro-Symbolic Programming |
| topic | Artificial Intelligence I.2.7 |
| url | https://arxiv.org/abs/2601.00743 |