aiqbench analysis
This survey provides a critical technical overview of rule-based languages like Datalog and answer set programming as symbolic components in neurosymbolic AI systems. By evaluating over 50 recent applications across databases, machine learning, vision, and robotics, it offers a practical decision matrix for selecting formalisms based on specific semantic and integration requirements. The analysis highlights key trade-offs between expressiveness, neural integration capabilities, and evaluation mechanisms that are essential for advancing hybrid AI architectures.
Rule-Based Languages for Neurosymbolic AI
arXiv:2610.07313v1 Announce Type: new Abstract: Logic programming is increasingly used as the symbolic component of neurosymbolic AI systems. We survey the main rule-based languages in this setting, namely Datalog, answer set, and probabilistic logic programs, along four axes: semantics, expressiveness, neural integration, and evaluation mechanism. We analyse over 50 recent systems and applications, comparing formalism usage across four research areas: databases and programming languages, machine learning, vision, and robotics. We provide a decision matrix mapping application scenarios to required features and close by outlining open problems.
Abstract:Logic programming is increasingly used as the symbolic component of neurosymbolic AI systems. We survey the main rule-based languages in this setting, namely Datalog, answer set, and probabilistic logic programs, along four axes: semantics, expressiveness, neural integration, and evaluation mechanism. We analyse over 50 recent systems and applications, comparing formalism usage across four research areas: databases and programming languages, machine learning, vision, and robotics. We provide a decision matrix mapping application scenarios to required features and close by outlining open problems.
Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)
arXiv:2610.07313 [cs.AI]
(or arXiv:2610.07313v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.07313 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 180 words
Related coverage
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · Sep 14, 2026
PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails
arXiv · Aug 19, 2026
Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering
arXiv · Jun 3, 2026
Learning Probabilistic Logic Programs with Functional Gradient Guided Language Models
arXiv · Oct 10, 2026