# Neural Decision-Propagation for Answer Set Programming

arXiv: https://arxiv.org/abs/2605.01797 · HTML: https://mlsanity.com/paper/2605.01797/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 52 references that are in the map.
- First posted on arXiv 3 May 2026.

## Builds on (most cited first, 13 of 13)

- [The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision](https://mlsanity.com/paper/1904.12584/) (2019)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [Learning Explanatory Rules from Noisy Data](https://mlsanity.com/paper/1711.04574/) (2017)
- [Learning a SAT Solver from Single-Bit Supervision](https://mlsanity.com/paper/1802.03685/) (2018)
- [NeurASP: Embracing Neural Networks into Answer Set Programming](https://mlsanity.com/paper/2307.07700/) (2023)
- [Neural-Symbolic Integration: A Compositional Perspective](https://mlsanity.com/paper/2010.11926/) (2020)
- [Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing](https://mlsanity.com/paper/2210.15889/) (2022)
- [Differentiable Programs with Neural Libraries](https://mlsanity.com/paper/1611.02109/) (2016)
- [A Neuro-Symbolic ASP Pipeline for Visual Question Answering](https://mlsanity.com/paper/2205.07548/) (2022)
- [Scalable Neural-Probabilistic Answer Set Programming](https://mlsanity.com/paper/2306.08397/) (2023)
- [Neuro-Symbolic AI for Compliance Checking of Electrical Control Panels](https://mlsanity.com/paper/2305.10113/) (2023)
- [Differentiable Logic Programming for Distant Supervision](https://mlsanity.com/paper/2408.12591/) (2024)
- [Towards end-to-end ASP computation](https://mlsanity.com/paper/2306.06821/) (2023)

## Built on by (most cited first, 1 of 1)

- [A Fully Differentiable Neuro-Soft-Symbolic Framework for Perceptual Task Planning](https://mlsanity.com/paper/2609.21221/) (2026)

## Abstract (arXiv)

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.