An Agentic Framework for Neuro-Symbolic Programming
This addresses the problem of time-consuming neuro-symbolic programming for both experienced and novice users, though it is incremental as it builds on the existing DomiKnowS framework.
The paper tackles the challenge of integrating symbolic constraints into deep learning models by proposing AgenticDomiKnowS (ADS), which translates free-form task descriptions into DomiKnowS programs, reducing development time from hours to 10-15 minutes.
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.