arXiv AI August 25, 2026 By Lihui Liu, Zihao Wang, Hanghang Tong

Neural-Symbolic Reasoning over Knowledge Graphs: A Survey from a Query Perspective

The article surveys neural-symbolic reasoning over knowledge graphs from a query perspective, highlighting the limitations of traditional symbolic methods when dealing with incomplete or noisy data. It discusses how the fusion of deep learning and symbolic reasoning—termed Neural Symbolic AI—offers interpretable and versatile solutions, and examines the role of large language models in advancing knowledge graph inference. The survey provides a comprehensive review of query types, classification of neural-symbolic approaches, and future directions for integrating LLMs with knowledge graph reasoning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

Hugging Face Trending Papers

Jun 10

LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems

Large Language Models (LLMs) have advanced rapidly, but their limitations in structured and multi-hop reasoning underscore the need for graph-native, synergistic artificial intelligence (AI) systems. Graph-structured data underpins critical applications across social, biological, financial, transportation, web, and knowledge domains, making it essential to understand how LLMs can leverage graph computation for grounded, context-rich inference.

llms agents

arXiv AI

Jun 11

LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems

arXiv:2606. 11560v1 Announce Type: cross Abstract: Large Language Models (LLMs) have advanced rapidly, but their limitations in structured and multi-hop reasoning underscore the need for graph-native, synergistic artificial intelligence (AI) systems.

By Arijit Khan, Longxu Sun, Xin Huang

llms agents

arXiv Machine Learning

Jun 5

Q-GNN: Query-Conditioned Graph Neural Networks with Type Awareness for Knowledge Graph Completion

arXiv:2606. 05639v1 Announce Type: new Abstract: Knowledge Graph Completion (KGC) aims at predicting missing triplets from incomplete knowledge graphs, which is crucial for downstream applications.

By Dongxiao He, Ruqiong Zhang, Zhizhi Yu, Ling Ding, Di Jin, Guangquan Xu, Zhiyong Feng

llms benchmarks

arXiv AI

Jun 19

Detecting Hallucinations for Large Language Model-based Knowledge Graph Reasoning

arXiv:2606. 19351v1 Announce Type: cross Abstract: Knowledge graph (KG) reasoning infers new knowledge from existing facts and is widely applied in question answering, recommendation, and decision support.

By Xinyan Zhu, Yaoqi Liu, Yue Gao, Huadong Ma, Cheng Yang, Chuan Shi

llms nlp benchmarks safety

arXiv AI

3d ago

Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction

arXiv:2605.29168v2 Announce Type: replace Abstract: Question answering (QA) is a core challenge in AI, particularly for complex queries requiring multi-hop reasoning across documents, or symbolic ope...

By Lorenzo Loconte, Timothy Hospedales, Cristina Cornelio

llms rag nlp data-engineering

arXiv AI

Jul 14

Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey

arXiv:2607. 09666v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) have emerged as a powerful paradigm in Knowledge Graphs (KGs) due to their intrinsic ability to model graph-structured data.

By Chengcheng Sun, Jiayun Tian, Cheng Zhai, Zhixiao Wang, Yajie Song, Xiaobin Rui, Jian Zhang, Philip S. Yu

rag

One email a morning, machine-written

Related stories

LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems

LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems

Q-GNN: Query-Conditioned Graph Neural Networks with Type Awareness for Knowledge Graph Completion

Detecting Hallucinations for Large Language Model-based Knowledge Graph Reasoning

Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction

Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey