cs.AIMay 3, 2026

Neural Decision-Propagation for Answer Set Programming

Authors: Thomas EiterKatsumi InoueSota Moriyama

Organizations: 1Vienna University of Technology (TU Wien), Austria · 2National Institute of Informatics, Japan · 3The Graduate University for Advanced Studies, SOKENDAI, Japan

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 propagations. Successful DProp computations are shown to capture the stable model semantics. We then develop Neural DProp (NDProp), a differentiable extension of DProp with neural computation for decisions and fuzzy evaluation for propagations. We evaluate the capabilities of NDProp for learning decision heuristics as well as neuro-symbolic integration, and compare it with existing neuro-symbolic approaches. The results show that NDProp can learn to efficiently compute stable models, and it improves accuracy and scalability on neuro-symbolic benchmarks.

Explore similar work

CardsList
  1. Distilling Answer Set Programming Theories from Large Language Models

    Jul 30, 2026Nelson Higuera Ruiz, Markus Hofmarcher, Claudiu Leoveanu-CondreiAnswer Set ProgrammingNeuro-Symbolic Framework