Neural Decision-Propagation for Answer Set Programming

📰 ArXiv cs.AI

Learn how Neural Decision-Propagation enhances Answer Set Programming with neural networks for scalable reasoning in Neuro-symbolic AI

advanced Published 5 May 2026

Action Steps

Implement Neural Decision-Propagation using Python and TensorFlow to compute stable models
Apply DProp to existing Answer Set Programming frameworks to enhance scalability
Configure neural networks to alternate falsity decisions and truth propagations
Test the performance of DProp on benchmark ASP problems
Compare the results with classical solvers to evaluate the improvement in scalability

Who Needs to Know This

Researchers and developers in AI, particularly those working on Neuro-symbolic AI and Answer Set Programming, can benefit from this approach to improve scalability in reasoning pipelines

Key Insight

💡 Neural Decision-Propagation (DProp) can improve the scalability of Answer Set Programming by alternating falsity decisions and truth propagations

Full Article

Title: Neural Decision-Propagation for Answer Set Programming

Abstract:
arXiv:2605.01797v1 Announce Type: new Abstract: Integration of Answer Set Programming (ASP) with neural networks has emerged as a promising tool in Neuro-symbolic AI. While existing approaches extend the capabilities of ASP to real world domains, their reasoning pipelines depend on classical solvers, which is a bottleneck for scalability. To tackle this problem, we propose a new method to compute stable models, called decision-propagation (DProp), which alternates falsity decisions and truth pro

Read full paper → ← Back to Reads