An Agentic Framework for Neuro-Symbolic Programming

2026-01-02

arXiv.org

AI Summary

This work proposes AgenticDomiKnowS (ADS), a novel framework that integrates symbolic constraints into deep learning through a large language model–based agent workflow, significantly lowering the barrier to developing neuro-symbolic programs. While incorporating symbolic knowledge enhances model robustness, interpretability, and data efficiency, existing approaches require users to master specialized programming syntax, limiting accessibility. ADS addresses this by automatically translating natural language task descriptions into executable DomiKnowS neuro-symbolic programs and enabling human-in-the-loop intervention to refine intermediate outputs. Through a modular generation-and-verification mechanism, the method preserves expert control while drastically reducing development time: both experienced and novice users can complete tasks in 10–15 minutes that previously required several hours, substantially improving the efficiency of neuro-symbolic program construction.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Cognitive Modeling & Cognitive Systems: Symbolic Representations
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• neuro-symbolic programming
• symbolic constraints
• deep learning integration
• declarative programming
• user proficiency

Innovation

• neuro-symbolic programming
• agentic framework
• declarative programming
• human-in-the-loop
• program synthesis