Answer Set Programming Energised! End-to-End Neurosymbolic Reasoning and Learning with ASP and Energy Based Models
Quick Answer
This paper introduces a neurosymbolic reasoning methodology that integrates answer set programming (ASP) with energy-based models, enabling robust end-to-end training for dynamic applications.
Quick Take
Key advancements include joint optimization in latent spaces and a practical implementation demonstrated with MNIST and evaluated against benchmarks like Clevr and MOT.
Key Points
- Introduces a modular integration of ASP with energy-based models for neurosymbolic reasoning.
- Supports joint optimization in continuous latent space with ASP-based declarative semantics.
- Demonstrates practical implementation using MNIST dataset.
- Evaluates performance on visual question-answering benchmark Clevr and multi-object tracking MOT.
- Advances the interface of answer sets and probabilistic logic for robust training.
Paper Resources
📖 Reader Mode
~2 min readAbstract:We present a general neurosymbolic reasoning and learning methodology based on a modular integration of answer set programming with an energy based model substrate. Key contributions are: (1) supporting joint optimisation in the continuous latent space through explicit ASP-based declarative semantics fully incorporating background knowledge, constraints, non-monotonic inference; and (2) advancing recent works at the interface of answer sets, probabilistic logic, and answer set modulo theories by providing a generalised model and practical platform for ASP-centric robust, end-to-end training for applications in dynamic domains (e.g., involving perception and interaction). We provide a practical implementation, and demonstrate basic use and application (with MNIST), and evaluate with the visual question-answering benchmark Clevr and the multi-object tracking benchmark MOT.
| Comments: | Preprint |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.08136 [cs.AI] |
| (or arXiv:2607.08136v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.08136 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mehul Bhatt [view email]
[v1]
Thu, 9 Jul 2026 06:18:35 UTC (3,723 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.