Latest Knowledge Graphs Research Papers

The newest Knowledge Graphs papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Knowledge Graphs 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.

Recent papers

• SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Data
  Wael AbdAlmageed · arXiv · Jul 22, 2026

  In many reasoning problems, the premises are not observed as discrete symbols, but must be inferred from high-dimensional inputs. Further, the predicate vocabulary, argument structure, and trusted evidence are supplied by a Knowledge Graph …

• AI4Deliberation_D4.1 – AI toolkit, Architecture and Knowledge Graph – first version
  Epameinondas Koutavelis, Evangelos Rigas, Gerasimos Papanikolaou-Ntais, Dimitris Zeginis et al. · Zenodo (CERN European Organ... · Jul 16, 2026

  This deliverable (D4.1) reports on the technical infrastructure of the AI4Deliberation project, consolidating the work of the first two sprints of Work Package 4 (Tasks T4.1 and T4.2). It documents the technical foundations that enable AI4D…

• Temporal-Weighted Transfer Network for Knowledge Graph Extrapolation
  Hongyu Hao, Yifan Zhang, Xinru Zhao, Jianfeng Lin et al. · ACM Transactions on Intelli... · Jul 15, 2026

  Temporal Knowledge Graph (TKG) reasoning aims to predict future events by analyzing historical snapshots across different timestamps, making it an important research direction. However, most existing methods rely either on probabilistic sta…

• Semantification of scientific articles using knowledge graphs
  Azanzi Jiomekong, Sanju Tiwari, Soren Auer · The Electronic Library · Jul 15, 2026

  Purpose This paper aims to propose an approach for the semantification of scientific papers so as to save the time of researchers in obtaining access to knowledge of their domain, comparing research contributions and getting novel insights.…

• A multimodal knowledge graph and two-stage reinforcement learning-based intelligent configuration approach of improvement design scheme for complex products
  Shan Ren, Guangli Yang, Xin Zhao, Ming Wang et al. · Journal of Engineering Design · Jul 14, 2026
• RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM
  Mikhail Komarov, Ivan Bondarenko, Stanislav Shtuka, Oleg Sedukhin et al. · arXiv · Jul 13, 2026

  Graph retrieval-augmented generation (GraphRAG) enhances large language models with structured knowledge, yet existing systems construct knowledge graphs in a single extraction pass, producing noisy entities and brittle retrieval. RAGU, an …

• Knowledge Graphs and Explainable AI as Complementary Resources for Urban Mining
  Jan Gronewald, Andreas Emrich, Nijat Mehdiyev · arXiv · Jul 10, 2026

  Pre-demolition assessment, the regulated audit process at the heart of urban mining, is an information process in which AI support must serve qualified auditors who remain accountable for the decisions taken. The relevant unit of value is n…

• Knowledge-graph attention network ChemFlow identifies modulators of EGFR
  Swarnava Samanta, Gaurava Srivastava, Saumya Ranjan Satrusal, Bernadette Mathew et al. · Cell Reports Physical Science · Jul 10, 2026
• mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA
  Xu Yuan, Liangbo Ning, Qingqing Ye, Wenqi Fan et al. · OpenAlex · Jul 10, 2026

  Retrieval-Augmented Generation (RAG) has emerged as an effective paradigm for expanding the knowledge capacity of Multimodal Large Language Models (MLLMs) by incorporating external knowledge sources into the generation process, and has been…

• Co-LMLM: Continuous-Query Limited Memory Language Models
  Yair Feldman, Linxi Zhao, Nathan Godey, Dongyoung Go et al. · arXiv · Jul 8, 2026

  Limited memory language models (LMLMs) externalize factual knowledge during pretraining to a knowledge base (KB), rather than memorizing it in their weights. During generation, the model then fetches knowledge from the KB as needed. This re…

• SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents
  Tianming Sha, Yue Zhao, Lichao Sun, Yushun Dong · arXiv · Jul 8, 2026

  Autonomous AI agents can execute complex tasks with limited human review, yet they often lack the grounded operational knowledge to make their outputs not just executable but correct, secure, and maintainable. We introduce SkillCenter, to o…

• Project-Level C-to-Rust Translation via Pointer Knowledge Graphs
  Zhiqiang Yuan, Yiling Man, Yu Yijun, Peng Xin · Open Research Online (The O... · Jul 5, 2026

  Translating C code into safe Rust is an effective way to ensure its memory safety. Compared to rule-based translation which produces Rust code that remains largely unsafe, LLM-based methods can generate more idiomatic and safer Rust code be…

• From Known Relations to New One: Learning to Classify Triplets of Unseen Relations from A Biomedical Knowledge Graph
  Pei Yuan Tsai, Chih‐Ping Wei, Hung-Ta Wu, J Li et al. · Journal of the Association ... · Jul 5, 2026

  Biomedical knowledge graphs (KGs) have become fundamental infrastructures for biomedical research and clinical decision support. However, large-scale biomedical KGs are predominantly constructed through automated extraction from scientific …

• Entity-Centric Retrieval-Augmented Generation with Knowledge-Graph Re-ranking for Biomedical Question Answering
  Che‐Jui Chang, Cheng-Ru Wei, Wei-Po Lee · Journal of the Association ... · Jul 5, 2026

  Retrieval-Augmented Generation (RAG) has emerged as an effective approach for grounding large language models with external knowledge. However, existing biomedical RAG systems primarily rely on semantic similarity and often fail to preserve…

• Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers
  Tianyi Li, Zhiqiang Shen · arXiv · Jun 22, 2026

  Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods typically optimize the interpolation path from only one model endpoint, limiting their …

• The More the Merrier: Combining Properties for ABox Abduction under Repair Semantics for ELbot
  Anselm Haak, Patrick Koopmann, Yasir Mahmood, Anni-Yasmin Turhan · arXiv · Jun 17, 2026

  Abduction is a central approach to explain missing entailments from a knowledge base by providing a hypothesis, that would, if added to the knowledge base, make the missing entailment become true. Abduction under repair semantics has recent…

• When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtime
  Wei Wu · arXiv · Jun 12, 2026

  LLM agent systems increasingly run as long-lived autonomous runtimes: scheduling jobs, calling tools, maintaining memory, and pushing results to humans. We present a longitudinal study of silent failures in one such system: a personal-assis…

• GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction
  ACL ARR 2026 May Submission · May 25, 2026

  Retrieval-Augmented Generation (RAG) enhances LLMs by grounding generation in query-relevant external evidence. Beyond unstructured text corpora, Graph RAG integrates knowledge graphs into the retrieval pipeline, enabling LLMs to access ent…

• SciToolAgent: a knowledge-graph-driven scientific agent for multitool integration
  Keyan Ding, Jing Yu, Junjie Huang, Yuchen Yang et al. · Nature Computational Science · Jul 27, 2025

  Scientific research increasingly relies on specialized computational tools, yet effectively utilizing these tools requires substantial domain expertise. While large language models show promise in tool automation, they struggle to seamlessl…

• LLM-DDI: Leveraging Large Language Models for Drug-Drug Interaction Prediction on Biomedical Knowledge Graph
  Dongxu Li, Yue Yang, Ziwen Cui, Hengchuang Yin et al. · IEEE journal of biomedical and health informatics · Jul 2, 2025

  Drug-drug interaction (DDI) refers to the interaction relationships between drugs. Discovering new DDIs is crucial for advancing drug development and enhancing clinical treatments. Given the significant progress achieved through graph neura…

• AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora
  Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong et al. · Annual Meeting of the Association for Computational Linguistics · May 29, 2025

  We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. Our system leverages large language models to simultaneously extract knowledge triples and induce compre…

• Large language model assisted fine-grained knowledge graph construction for robotic fault diagnosis
  Xingming Liao, Chong Chen, Zhuowei Wang, Ying Liu et al. · Advanced Engineering Informatics · May 1, 2025

  With the rapid deployment of industrial robots in manufacturing, the demand for advanced maintenance techniques to sustain operational efficiency has become crucial. Fault diagnosis Knowledge Graph (KG) is essential as it interlinks multi-s…

• CKGFuzzer: LLM-Based Fuzz Driver Generation Enhanced By Code Knowledge Graph
  Hanxiang Xu, Wei Ma, Ti Zhou, Yanjie Zhao et al. · 2025 IEEE/ACM 47th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · Apr 27, 2025

  In recent years, the programming capabilities of large language models (LLMs) have garnered significant attention. Fuzz testing, a highly effective technique, plays a key role in enhancing software reliability and detecting vulnerabilities.…

• Digital twin system for manufacturing processes based on a multi-layer knowledge graph model
  Chang Su, Xin Tang, Qi Jiang, Yong Han et al. · Scientific Reports · Apr 14, 2025

  Digital twin technology in the manufacturing process faces challenges like integrating diverse data sources and managing real-time data flow. To address this, we propose a novel three-layer knowledge graph architecture to enhance digital tw…

• Knowledge Graph Construction: Extraction, Learning, and Evaluation
  Seungmin Choi, Yuchul Jung · Applied Sciences · Mar 28, 2025

  A Knowledge Graph (KG), which structurally represents entities (nodes) and relationships (edges), offers a powerful and flexible approach to knowledge representation in the field of Artificial Intelligence (AI). KGs have been increasingly a…

• Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning
  Junming Liu, Siyuan Meng, Yanting Gao, Song Mao et al. · IEEE International Conference on Computer Vision · Mar 17, 2025

  Multimodal reasoning in Large Language Models (LLMs) struggles with incomplete knowledge and hallucination artifacts, challenges that textual Knowledge Graphs (KGs) only partially mitigate due to their modality isolation. While Multimodal K…

• Construction of a knowledge graph for framework material enabled by large language models and its application
  Xuefeng Bai, Song He, Yi Li, Yabo Xie et al. · npj Computational Materials · Feb 27, 2025

  Framework materials (FMs) have been extensively investigated with a plethora of literature documenting their unique properties and potential applications. Despite this, a comprehensive knowledge graph for this emerging field has not yet bee…

• How Expressive are Knowledge Graph Foundation Models?
  Xingyue Huang, Pablo Barceló, Michael M. Bronstein, I. Ceylan et al. · International Conference on Machine Learning · Feb 18, 2025

  Knowledge Graph Foundation Models (KGFMs) are at the frontier for deep learning on knowledge graphs (KGs), as they can generalize to completely novel knowledge graphs with different relational vocabularies. Despite their empirical success, …

• Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering
  Runxuan Liu, Bei-Bei Luo, Jiaqi Li, Baoxin Wang et al. · Annual Meeting of the Association for Computational Linguistics · Feb 17, 2025

  Large language models (LLMs) have shown remarkable capabilities in natural language processing. However, in knowledge graph question answering tasks (KGQA), there remains the issue of answering questions that require multi-hop reasoning. Ex…

• Knowledge Graph-Guided Retrieval Augmented Generation
  Xiangrong Zhu, Yuexiang Xie, Yi Liu, Yaliang Li et al. · North American Chapter of the Association for Computational Linguistics · Feb 8, 2025

  Retrieval-augmented generation (RAG) has emerged as a promising technology for addressing hallucination issues in the responses generated by large language models (LLMs). Existing studies on RAG primarily focus on applying semantic-based ap…