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
- A tiered deep learning and symbolic reasoning framework for safe, explainable disease diagnosisAbdulrahman Khaled Ali Odhaib, Rana Zaki Ali Abdulrahman Al-Maflehi, Niayesh Gharaei, Cemal Gemci · Scientific Reports · Sep 10, 2026
This study introduces a modular, AI-powered disease diagnosis system that combines deep learning, neuro-symbolic reasoning, and structured automation to support early, scalable, and explainable clinical decision-making. Built upon the large…
- Combining Formal Reasoning and LLMs for Scenario-Based Educational STEM ExercisesLuisa Vollmer, Rébecca Loubet, Daniel Neider, Hans Hasse et al. · Human-Centric Intelligent S... · Sep 10, 2026
Abstract Large language models (LLMs) enable scalable generation of educational exercises for science, technology, engineering, and mathematics (STEM) but often produce mathematically invalid or physically inconsistent problems, while manua…
- Hierarchical conditional memory for cross-vocabulary medical entity linkingYunguo Yu · Informatics in Medicine Unl... · Sep 7, 2026
Objective: To introduce HyCoM (Hierarchical Conditional Memory), a neuro-symbolic framework that decouples static ontology retrieval from dynamic contextual reasoning for extremescale cross-vocabulary medical entity linking, with emphasis o…
- Federated Neuro-Symbolic Learning for Privacy-Preserving Intelligent Edge SystemsRushikesh Shantaram Bhalerao, Suvarna Lahanu Ghogare, satish tukaram pokharkar, Sweety Godhiram Jachak et al. · International Journal of Co... · Sep 7, 2026
Intelligent Edge Systems – smart cameras, wearable technology, connected cars and industrial sensors – are creating a growing need to learn from local data at the edge. The two main lines of research that have attempted to address this prob…
- Embedding Moral Experience: A Neuro-Symbolic Agent with Structured Ethical Memory for Internally Justifiable Decision-MakingAhlam Awwad, Mutaz Abu Sara, Jawad Alkhateeb, Dahaman Ishak · Journal of Sustainable Smar... · Sep 4, 2026
Empowering artificial intelligence to make morally sound decisions is crucial, as these systems are increasingly deployed in ethically delicate fields like autonomous driving and healthcare. Achieving robust moral decision-making remains a …
- Symbolic Constraints Improve Metacognitive Efficiency in Neuro-Symbolic AIMichael Clopton, Sven Thijssen · NeSy 2026 · Sep 1, 2026
Neuro-symbolic AI (NeSy) is an emerging paradigm that combines neural inference with logical reasoning to improve model predictive performance across a wide variety of tasks, including classification, visual reasoning, autonomous planning, …
- NL2AGBench: Benchmarking LLM Auto-Formalization for AlphaGeometrySamuel Xiao, Judy Song, Rory Hu, Ziliang Zong · arXiv · Aug 28, 2026
Recent advances in large language models (LLMs) have demonstrated strong capabilities in natural language understanding and mathematical reasoning. However, their ability to translate informal mathematical problems into formal representatio…
- Neurosymbolic Large Language Models: A Survey of Symbolic Integration, Reasoning and ExplainabilityManeeha Rani, Bhupesh Kumar Mishra, Dhavalkumar Thakker · Information Systems Frontiers · Aug 28, 2026
Abstract LLMs have demonstrated strong language-learning and human-like response-generation capabilities, and they are increasingly used to support decision-making in high-risk sectors. However, their internal decision processes remain diff…
- From Ambiguity to Execution: An Agentic Neuro-Symbolic Framework for Transforming Building Regulations into Deterministic ConstraintsNikoo Mirhosseini, D. Shojaei, Soheil Sabri · Buildings · Aug 27, 2026
Integrating Large Language Models (LLMs) into Automated Compliance Checking (ACC) introduces "Spatial Hallucinations" and "Serialization Bottlenecks" when processing massive Building Information Models (BIM). This research proposes an Agent…
- NEXAR-Maint: a neurosymbolic explainable augmented reality framework for predictive maintenance and troubleshooting in Industry 4.0Sara Scheffer · The International Journal o... · Aug 27, 2026
Abstract The rapid evolution of Industry 4.0 and the convergence of Information Technology (IT) and Operational Technology (OT) have increased the complexity of industrial maintenance and troubleshooting. Cyber-Physical Production Systems (…
- Compositional neurosymbolic representations enable efficient active explorationP. Michael Furlong, Nicole Sandra-Yaffa Dumont, Rika Antonova, Jeff Orchard et al. · Nature Communications · Aug 22, 2026
Abstract Autonomous systems that learn and explore over long horizons face a problem. Standard methods scale poorly in the number of observations, n , precluding sustained operation on bounded hardware. We show that compositional, high-dime…
- Neuro-Symbolic Guardrails: Why Agentic AI Systems Need Ontologies A Survey and Architectural Analysis of Ontology-Constrained LLM Agent LoopsP. Niranjan · OpenAlex · Aug 22, 2026
- A Neuro-Symbolic framework for trustworthy agentic AI in industrial code reviewJihyun Park, Yong Gyu Kim · Information and Software Te... · Aug 20, 2026
- Основни принципи и философски аспекти на невросимволния изкуствен интелектDoroteya Angelova · Философски алтернативи · Aug 20, 2026
The present article aims to examine the main factors that have led to the emergence of hybrid approaches in the field of artificial intelligence and mainly of neuro-symbolic artificial intelligence. It is primarily concerned with clarifying…
- From Perception to Reasoning: Knowledge Graphs, Neuro-Symbolic AI, and Explainable Artificial Intelligence in Autonomous VehiclesPatrik Viktor, Gábor Kiss · Machine Learning and Knowle... · Aug 20, 2026
Autonomous vehicles increasingly require capabilities that extend beyond perception towards contextual understanding, semantic reasoning, and explainable decision-making. Knowledge graphs (KGs) have emerged as a promising solution by integr…
- On the Fragility of Self-Improving Agents: Variance, Task Order, and UnderspecificationQinyuan Ye, Yu Li, Yada Pruksachatkun, Jiaxin Zhang et al. · arXiv · Aug 18, 2026
Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature. However, the reliability aspects of these methods…
- Towards Zero-Shot Task Transfer with Neurosymbolic World ModelsIsidoro Tamassia, Lennert De Smet, Giuseppe Marra · arXiv · Aug 18, 2026
State-of-the-art model-based reinforcement learning methods learn neural world models that allow policy improvement by planning in a latent space, without assumptions on the structure of the underlying environment. While expressive, these m…
- Neurosymbolic Embodied AgentsMohammad Albinhassan, Yuming Feng, Alessandra Russo, Pranava Madhyastha · arXiv · Aug 17, 2026
Language and vision-language models generate plausible embodied plans but do not guarantee executability, as their outputs can violate environment dynamics or act on incorrectly grounded entities. We present a neurosymbolic agent that facto…
- Neuro-symbolic ophthalmology: A Temporal–Multimodal Concept Bottleneck framework for interpretable glaucoma progression predictionMohammad Tanhaei · Intelligence-Based Medicine · Aug 17, 2026
Deep learning models now match the accuracy of eye doctors in diagnosing eye diseases. But these models work like black boxes. This lack of openness is a big problem for use in clinics. Clinics need clear reasons for decisions. We introduce…
- Reasoning Beyond Prediction: A Neuro-Symbolic Multi-Agent Framework for Explainable Options TradingPartha P. Adhikari, Vineeta Khemchandani, Neetu Sharma · International Journal of Co... · Aug 17, 2026
Price-direction prediction has long been treated as the central task in building automated trading systems. What such systems rarely address is whether a proposed trade makes economic sense, sits within an acceptable risk envelope, or can b…
- The Neuro-Symbolic Attack SurfaceRichard Barron · Zenodo (CERN European Organ... · Aug 17, 2026
Neuro-symbolic (NeSy) AI systems — hybrid architectures combining neural perception with symbolic reasoning engines — introduce a distinct attack surface that existing AI security tools do not address. All prior AI security tooling assumes …
- The Neuro-Symbolic Attack SurfaceRichard Barron · Zenodo (CERN European Organ... · Aug 17, 2026
Neuro-symbolic (NeSy) AI systems — hybrid architectures combining neural perception with symbolic reasoning engines — introduce a distinct attack surface that existing AI security tools do not address. All prior AI security tooling assumes …
- Neuro-Symbolic AI for the Insurance Placement Process Integrating Statistical Learning with Symbolic Reasoning to Transform Broker Submission, Triage, and Risk Placement in Commercial InsuranceAakash Angadi · International Journal of Co... · Aug 17, 2026
Insurance placement — the process by which a broker-submitted risk is matched, priced, negotiated, and bound with one or more carriers — remains one of the most complex and judgment-intensive workflows in financial services. Despite heavy i…
- Compositional Neural-Cyber-Physical System Verification in the Interactive Theorem Prover of Your ChoiceMatthew L. Daggitt, Ekaterina Komendantskaya, Alistair Sirman, A. Bruni et al. · Proceedings of the ACM on P... · Aug 17, 2026
Formal verification of neuro-symbolic cyber-physical systems, such as drones, medical devices and robots, is complicated. Neural components must be trained to be optimal with respect to the available data as well as the safety specification…
- A Blockchain-Enabled Federated Neuro-Symbolic Framework for Secure Wearable Biosensor-Based Health MonitoringKhulud Salem Alshudukhi, Noshina Tariq · Biosensors · Aug 16, 2026
Wearable biosensors generate continuous physiological data in smart Internet of Disease (IoD) environments. These data can support early disease detection and remote patient monitoring. However, wearable data are often noisy, sensitive, and…
- From shape grammars to machine learning: a plea for the neuro-symbolic approach to generative AIMario Carpo · Architectural Intelligence · Aug 13, 2026
Abstract A comparison between examples of style transfer and stylistic imitation as envisaged by the theory of Shape Grammars in the 1970s and those enabled by Generative AI today (with case studies and student work from a research seminar)…
- VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use PoliciesAnkita Rajaram Naik, Anupama Murthi, Benjamin Elder, Siyu Huo et al. · arXiv · Aug 12, 2026
Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation. We introduce VAKRA (e\textbf{V}aluating \textbf{A}PI and \textbf{K}nowledg…
- sLTN: Structural Logic Tensor NetworksDavide Rinaldi, Luciano Serafini · arXiv · Aug 11, 2026
Logic Tensor Networks (LTN) provide a neurosymbolic framework in which first-order logic is interpreted through tensor operations, enabling logical constraints to be integrated with differentiable learning. However, the original formulation…
- Neuro-Symbolic AI for Verifiable Reasoning in Regulated Enterprise WorkflowsJeffery Podolski, Xinchen Lyu · OpenAlex · Aug 11, 2026
- A neuro-symbolic approach to translate English to logic and ontologyAdam Pease, Richard Thompson · Frontiers in Artificial Int... · Aug 7, 2026
Human language is often vague and ambiguous. There have been many efforts to create formal languages and many attempts to translate human language into formal languages. Logic has a great deal of flexibility, not least in how the symbols us…