Latest Neuro-Symbolic AI Research Papers
The newest Neuro-Symbolic AI papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Neuro-Symbolic AI so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.
Get the latest Neuro-Symbolic AI papers in your inbox — free →Recent papers
- Hybrid AI Patterns: Thirteen Ways to Couple Language Models with Rules, and How to Choose Among ThemSiegfried Handschuh, Götz-Henrik Wiegand, Lorena Raichle · arXiv · Oct 29, 2026
Language models handle text well, and rule engines give conclusions with proofs. Systems that combine the two are usually described by example, and the same coupling turns up under different names in agent frameworks, guardrail toolkits and…
- Data Physics & L0-ISM : Layer 0 Invariant State Matrix & Neuro-Symbolic AI Safety Framework (Software Release).Rajmund Olszewski · Zenodo (CERN European Organ... · Oct 28, 2026
Description (Abstract): This software deposit establishes the formal Prior Art and baseline release (v1.0.1) for the Layer 0 Invariant State Matrix (L0-ISM)—a deterministic cyber-physical framework designed to mathematically eliminate Large…
- TimestralAdrien Petralia, Alexandre Gavaudan, Artjom Joosen, Etienne Goffinet et al. · arXiv · Oct 27, 2026
We introduce Timestral, a family of four time series foundation models for probabilistic forecasting, with 5M, 28M, 123M, and 209M parameters. Timestral sets a new state of the art on GIFT-Eval, TIME, and fev-bench, where Timestral-209M and…
- M4Bench: Evaluating Procedural Specification for Clinical EHR Derivation AgentsHannes Ill, Rafi Al Attrach, Rajna Fani, Ahram Han et al. · arXiv · Oct 27, 2026
Clinical research over electronic health records depends on derived variables whose definitions sit outside the schema, in item codes, time windows, missingness rules, and output-grain choices that change cohorts and downstream conclusions.…
- Ranking Function Generation with LLMs for TerminationRongkang Li, Jiaxin Hu, Taolue Chen, Yong Li et al. · arXiv · Oct 26, 2026
Ranking functions are a fundamental technique for proving loop termination, but constructing them manually is challenging and requires substantial expertise. We propose RAINFALL, a neuro-symbolic framework which follows the generate-verify-…
- NeSySpec: Neuro-Symbolic Technical Intelligence for Auditing Engineering Specifications with an Application to AircraftPier Mattia Basciano, Gianvito Antenori, Cristiano Andolfi, Giovanni Farina et al. · arXiv · Oct 26, 2026
Engineers who audit a declared specification of an engineered system need to know which physical constraints it respects, which it violates, which field was altered and how to correct it. NeSySpec is an integrated and interpretable neuro-sy…
- A Collaborative Knowledge Graph Development Agent for Neurosymbolic AI AgentsSpencer M. Seals · ceur-ws.org · Oct 26, 2026
- Selected Research Directions in NeuroSymbolic AIMichael McCain, Antrea Christou, Chris Davis Jaldi, Elham Ghiasi et al. · ceur-ws.org · Oct 26, 2026
- Ontology-enabled neuro-symbolic closed-loop control of laser powder bed fusionGisuk Hong, Jaebong Cho, Hyunbo Cho · Journal of Intelligent Manu... · Oct 26, 2026
A geometry-conditioned, neuro-symbolic closed-loop architecture is proposed for laser powder bed fusion, in which an ontology aligned with established standards and domain vocabularies operates inside the control loop and couples symbolic r…
- Spatially Grounded Neurosymbolic AI for Explainable Retinal Disease Classification From OCT ImagesLeandro Inferrera, Alessandro Biscontin, Miloš Ajčević, Agostino Accardo et al. · Translational Vision Scienc... · Oct 23, 2026
Purpose: To develop and evaluate a spatially grounded neurosymbolic AI framework for explainable multilabel retinal disease classification from optical coherence tomography (OCT) images, integrating convolutional neural network (CNN)-based …
- Beyond learning and reasoning: Meta-cognition for AI working inside complex systemsAlexiei Dingli · PLOS complex systems. · Oct 23, 2026
Neuro-symbolic AI combines statistical learning with symbolic reasoning, offering a promising path towards more trustworthy artificial intelligence.Yet when viewed through the lens of complexity science, another capability becomes essential…
- FairFRESH: A Neuro-Symbolic Framework for Fair and Explainable Household Food RecommendationKodur Sai Vinay Sathvik, Kakoli Bora, Tejaswini R. M · arXiv · Oct 22, 2026
Recommender systems typically serve one user at a time. However, in households, members share a finite pantry and follow different dietary rules, making independent recommendations prone to resource conflicts and dietary violations. We form…
- SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate ProgramsArnon Mazza, Elad Levi · arXiv · Oct 22, 2026
Policy enforcement for LLM agents has shifted from single-turn content moderation to compound, application-specific policies evaluated over multi-turn transcripts and tool-call trajectories. Fine-tuned guardrail models are efficient but deg…
- Data Physics in Edge AI Architecture - Part XII: The Hydrodynamic Paradox of Edge AI: Venturi Effect in SLM Quantization and Neuro-Symbolic Ejector Architectures.Rajmund Olszewski · Zenodo (CERN European Organ... · Oct 22, 2026
Title: The Hydrodynamic Paradox of Edge AI: A Neuro-Symbolic L0 Architecture for Critical Infrastructure Abstract: Deploying probabilistic, cloud-based artificial intelligence models (LLMs) in critical infrastructure systems (OT, e.g., mCDU…
- Ontology-guided neuro-symbolic convNeXtV2–swin transformer for explainable cytological classification of papillary thyroid carcinomaIbrahim Abdulrab Ahmed, Ebrahim Mohammed Senan, Awad Alyousef, M. Attique Khan et al. · Scientific Reports · Oct 22, 2026
Abstract The cytological assessment of papillary thyroid carcinoma (PTC) relies on microscopic evaluation of cellular and nuclear morphology. Subtle cytomorphological differences, interobserver variability, and specimen heterogeneity can co…
- A psychological prediction automatic reasoning framework for explaining potential cognitive statesFanjie Xu · Discover Artificial Intelli... · Oct 22, 2026
Psychological prediction, the ability to infer human behavior and intentions, is essential for artificial intelligence and human–machine interaction. Existing deep learning models often rely on surface-level fitting and lack structured abdu…
- UK Design Patent: Computer Display Screen with Adaptive Learning Interface, Eman Zaki Mousa Mohamed ElsherifEman Zaki Mousa Mohamed · Zenodo (CERN European Organ... · Oct 20, 2026
The present invention relates generally to the field of artificial intelligence in education, and more specifically to neuro-symbolic AI systems, cognitive digital twins, federated learning architectures, and multi-agent systems for adapti…
- Kronecker Delta Rule for Long Context Linear AttentionAnamaria-Roberta Hartl, Levente Zólyomi, Michael List, Günter Klambauer et al. · arXiv · Oct 19, 2026
We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision mechanism that corrects targeted associati…
- Machina Pauliana: A neuro-symbolic approach to the actio pauliana in Dutch insolvency lawDaan Boven, Gregor Behnke, David Graus · arXiv · Oct 19, 2026
Applying a legal provision frequently requires both structured rule-based reasoning and sensitivity to open-textured terms developed in case law. The actio pauliana of Article 42 of the Dutch Bankruptcy Act (Faillissementswet, Fw), which al…
- Beyond Monumentality: An Integrated Framework of UAV- Borne Remote Sensing, Soil Bio-Geochemistry, and Neurosymbolic AI for Landscape Archaeology and Battlefield ProspectionNoah Ugur Kilinc · OpenAlex · Oct 19, 2026
- CHERI: An Agentic AI Framework for Structural Quality Control of Excel-Based Budget Impact ModelsBehnam Sharif, Arash Ajdari · Zenodo (CERN European Organ... · Oct 19, 2026
Objectives: Excel-based health economic (HE) models encode their logic implicitly across worksheets, formulas and layout, which limits what large language model (LLM) agents can reliably understand and check. We developed CHERI, an agentic,…
- PERTARO: Cache-Bounded Neuro-Symbolic Micro-Experts via Seed-Compressed Ternary Tries and Periodic Answer Set RegroundingSean Everett Morin · Zenodo (CERN European Organ... · Oct 18, 2026
Neuro-symbolic systems and sparse Mixture-of-Experts(MoE) architectures face competing structural pressures:Answer Set Programming (ASP) solvers suffer from combinatorial rule explosion when grounding deep sequentialhorizons, while micro-ex…
- Commonsense Knowledge and Its Representation in Artificial Intelligence: A Conceptual Review of Symbolic, Graph-Based, Neural, and Neuro-Symbolic ApproachesNdiana Okon Asuquo (PhD Candidate), Ubon Asuquo Obonguko · Zenodo (CERN European Organ... · Oct 18, 2026
Commonsense knowledge comprises the everyday facts, expectations, causal assumptions, social conventions, Physical regularities, and practical inference patterns that people ordinarily use without explicitly stating them. Although artificia…
- SymbolFusion uses relation constraints in neurosymbolic graph learning to model literary structure and emotion trajectoriesYuhang Du · Discover Artificial Intelli... · Oct 17, 2026
Abstract Literary texts contain recurring imagery, typed symbolic relations, and long-range emotion shifts that sequence models do not represent explicitly. This paper presents SymbolFusion, a relation-constrained neuro-symbolic graph frame…
- Multi-Perspective explainability in traffic prediction: A neuro-symbolic approach using CNN-LSTMs and concept latticesSuraya Syazwani Mohamad Yusof, Hadhrami Ab Ghani, Nurul Izrin Md Saleh, Nurulaqilla Khamis · Applied Intelligence · Oct 17, 2026
The rapid urbanization and continuous growth of vehicle ownership have escalated traffic congestion into a critical socioeconomic challenge, resulting in massive productivity losses and environmental degradation. To establish effective Inte…
- LLM-BASED NEURO-SYMBOLIC LEGAL JUDGMENT PREDICTION FOR CRIMINAL CASESInternational Research Jour... · Oct 16, 2026
Predicting the outcome of a criminal case involves more than recognising which offence a narrative resembles.A court asks whether each ingredient of the offence has been proved, whether a lesser offence still applies when one ingredient fai…
- A Lifelong Neuro-Symbolic Explainable AI Twin for Zero-Touch 6G IoE Management Under Non-Stationary Network DynamicsWalaa M. Alayed, Hassam Ahmed Tahir, Waqar Ul Hassan · Electronics · Oct 16, 2026
Future sixth-generation (6G) Internet of Everything (IoE) networks require zero-touch management systems capable of autonomously allocating communication and computational resources, satisfying service-level constraints, and providing trans…
- OntoAct: Hypothesis-Based Neuro-Symbolic Agents through Ontological AbstractionDonghyeok Lee, Bong Gyun Kang, Junyong Ahn, Sungroh Yoon · arXiv · Oct 15, 2026
Learning from experience requires recovering reusable knowledge and determining when it applies to a new situation. We introduce OntoAct, a hypothesis-based neuro-symbolic framework built on ontological abstraction. OntoAct turns individual…
- An evaluation guided multiagent framework for generating floor plans that comply with municipal building regulationsAarnav Kembhavi, Aryan Rai, Prakhar Parashar, Ananmay A Lohia et al. · Discover Artificial Intelli... · Oct 15, 2026
Abstract Generative models often produce perceptually plausible outputs that violate hard domain rules. In architectural layout generation, balancing geometric intuition with regulatory compliance remains a persistent challenge, as current …
- KnowTD Interface: An Interactive Neuro-Symbolic Workflow for Thermodynamics Problem SolvingLuisa Vollmer, Rébecca Loubet, Hans Hasse, Heike Leitte · ceur-ws.org · Oct 15, 2026