Knowledge Graphs

Also known as KG

Knowledge graphs organize facts as entities, relations, and often schemas or provenance, making information from different sources easier to connect, query, and inspect. Work spans graph construction from text and databases, entity alignment and completion, and reasoning with ontologies, rules, embeddings, and graph neural networks. Large language models are increasingly used to build and query graphs, often combining graph traversal with retrieval to answer multi-hop questions in domains such as medicine, science, and law. A central challenge is ensuring graphs are complete, consistent, and well-evidenced at scale; benchmarks also need to test genuine multi-hop reasoning rather than simpler link prediction, while preserving the traceability that makes graph-based answers useful.

Latest papers

232 papers19 papers in the last four weeks, down 47% on the four weeks before. 0.1% of all new papers.

Prospector: learning a compact graph traversal policy for scientific reasoning
Oct 27, 2026Haiqian Yang, Markus J. BuehlerLLM Reasoning with Graphs Scientific Reasoning in Language Models
Department of Civil and Environmental Engineering Department of Mechanical Engineering Schwarzman College of Computing Massachusetts Institute of Technology Cambridge, MA, USA
An Incremental Knowledge-Graph Learner Digital Twin for Evidence-Grounded Early Warning
Oct 27, 2026Ngoc Luyen Le, Marie-Hélène Abel, Bertrand LaforgeEarly Warning Detection Digital Twins
Gamaizer, 93340 Le Raincy, France · Université de technologie de Compiègne, CNRS, Heudiasyc (Heuristics and Diagnosis of Complex Systems), CS 60319, 60203 Compiègne Cedex, France · Sorbonne Université, CNRS UMR 7585, LPNHE (Laboratoire de Physique Nucléaire et des Hautes Énergies), 75252 Paris Cedex 05, France
Agreement Between Reconstructed and Native GDELT GKG Records: A Field-Level Baseline
Oct 26, 2026Nikita A. KliminKG Construction Document Information Extraction
HSE University, Moscow, Russia
An Empirical Study of Recent Large Language Models for Knowledge Graph to Text Generation on Standard Benchmarks
Oct 22, 2026Priyanka, Renaud Delbru, Souhail Bakkali +2Knowledge Graphs LLM Evaluation
La Rochelle Université, La Rochelle, France · Siren, Bordeaux, France · Université de Rennes, Rennes, France
SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs
Oct 22, 2026Yifan Yuan, Yancheng Zhu, Zuoyu Zhang +1Knowledge Graphs Grounded Text Generation
School of Artificial Intelligence, Shenzhen University, Shenzhen, China
ChronoSynth: Constraint-Aware Question Synthesis over Temporal Knowledge Graphs
Oct 21, 2026Feng Liang, Weixin Zeng, Runhao Zhao +3Knowledge Graphs Temporal KGs
National Key Laboratory of Big Data and Decision, National University of Defense Technology, China · Beijing University of Posts and Telecommunications, China
Semantic Observability for Autonomous Systems Diagnostics
Oct 20, 2026Jitendra Solanki, Anand Todkar, Ziran MinRoot Cause Analysis Knowledge Graphs
Siemens Corporation, Princeton, NJ, USA
RANGER: Retrieval Agent for Navigating Graphs with Semantic Evaluation Rewards
Oct 20, 2026Artem Mikhaylov, Pavel Konoplev, Nikolay Efanov +2Knowledge Graph Question Answering LLM-Guided RL
Skolkovo Institute of Science and Technology (Skoltech), Moscow, Russia · Moscow Institute of Physics and Technology (MIPT), Moscow, Russia · AIRI, Moscow, Russia
How Benchmark Graph Construction Shapes Multi-Hop KG Navigation: A Controlled Audit of PathQuestion and PathQuestion-Large
Oct 19, 2026Eduin E. Hernandez, Sergio A. Diaz, Luis F. Garcia +2Graph Construction Knowledge Graph Question Answering
National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Independent Researcher
Bridging Concepts: Multi-Agent Reasoning over Scientific Concept Graphs for High-Impact Research Prediction
Oct 18, 2026Donggyu Yoon, Minsung Hwang, Juneha Baek +2Knowledge Graphs LLM Reasoning with Graphs
School of Computing, KAIST · College of Business, KAIST · Department of AI Computing, KAIST
Reranking Answers of Large Language Models with Knowledge Graphs
Oct 18, 2026Mikhail Salnikov, Hai Le, Olga Tsymboi +6Knowledge Graph Question Answering Knowledge Graphs
Artificial Intelligence Research Institute, Moscow, Russia · Skolkovo Institute of Science and Technology, Moscow, Russia · Sber AI Lab, Moscow, Russia +3
SQuIREL: A Context-Relative Framework for Measuring Entity Richness in Wikidata
Oct 17, 2026Michelle Nwachukwu, Albert Meroño-Peñuela, Martim BrandãoKnowledge Graphs
King’s College London, London, United Kingdom
Graph Serializations for Reasoning LLMs: A Study Across Knowledge Extraction and Structural Reasoning
Oct 15, 2026Julien Yu, Mihaela Bornea, Avirup Sil +1LLM Reasoning with Graphs Knowledge Graphs
Oracle
QORH: Learning Query-Specific Ordered Rule Hypergraphs for Inductive Knowledge Graph Link Prediction
Oct 13, 2026Naixing XuKnowledge Graphs KG Completion
School of Software, Shandong University, Jinan, China
Keep Your Receipts: Trustworthy Cleanup of Agent-Built Knowledge Graphs
Oct 13, 2026Vishisht ChoudharyKnowledge Graphs Data Provenance
Technical University of Munich
Faithful and Complete LLM-Assisted Automated Construction of Hierarchical Hardware Knowledge Graphs
Oct 8, 2026Haotian Qiao, Robert P. DickKG Construction Knowledge Graphs
Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor, MI, USA
U4RASD at KnowledgeGraphEval-2026: Ontology-Constrained Encoder and LLM Systems for Arabic Relation Extraction
Oct 8, 2026Ahmad Abbas, Hussein Mazeh, Chadi Abou Chakra +3Relation Extraction Arabic NLP
Arab Center for Research and Policy Studies, Doha · American University of Beirut, Beirut, Lebanon
From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue
Oct 8, 2026Zirui Liao, Zhengxian Wu, Zhuohong Chen +4Long-Term Conversational Memory Agentic RAG
Tsinghua University Shenzhen International Graduate School, Shenzhen, China
Reliability of LLM Judges for Evaluating Entity Alignment
Oct 7, 2026Vaibhava Lakshmi Ravideshik, Mayank KejriwalKG Entity Alignment LLM-as-a-Judge
University of Michigan, Ann Arbor · Information Sciences Institute, University of Southern California
Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing
Oct 6, 2026Remo Grillo, Lukas Klic, Giovanni ColavizzaLLM Grounding Knowledge Graphs
University of Bologna, Via Zamboni 33, 40126 Bologna, Italy · I Tatti — The Harvard University Center for Italian Renaissance Studies, Via di Vincigliata 26, 50135 Florence, Italy · Department of Communication, University of Copenhagen, Karen Blixens Plads 8, 2300 Copenhagen S, Denmark
Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents
Oct 5, 2026Mohamed Chenene, Carlos Rosas-Hinostroza, Anastasia Stasenko +2Multi-Hop QA Knowledge Graph Question Answering
PleIAs · Lattice, ENS-PSL, CNRS, Sorbonne Nouvelle · Université Paris Dauphine-PSL +4
Training-Free Clinical Reasoning through Medical Ontologies and Cognitive Mapping: A Symbolic-Probabilistic Knowledge Graph Framework
Sep 28, 2026Surajit DasSymbolic Reasoning Clinical Reasoning
Nutri-ATLAS: Embodied Agent for Tabulated Lookup and Assistance for Smarter nutrition
Sep 26, 2026Uttej Kallakuri, Boxun Hu, Ankur A. Butala +2Embodied AI LLM Reasoning with Graphs
Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218 USA · Geriatric Engineering at Johns Hopkins University, Baltimore, MD 21218 USA · Departments of Neurology and Neurosurgery, Johns Hopkins Medicine, Baltimore, MD 21287 USA
Do LLMs Understand Context? A Knowledge Graph-Based Evaluation Framework
Sep 24, 2026Subavarshana Arumugam, Mamta Nallaretnam, Kithuni Wickramasinghe +4LLM Evaluation LLM Grounding
Department of Computer Science & Engineering, University of Moratuwa, Sri Lanka · Department of Electrical and Computer Engineering, University of Miami, USA
CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding
Sep 24, 2026Federico Pennino, Andrea Gurioli, Stefano Zacchiroli +2KG Construction LLM Information Extraction
Università di Bologna Bologna, Italy · LTCI Télécom Paris, Institut Polytechnique de Paris Palaiseau, France · DISI Università di Bologna Bologna, Italy +1
The Path Matters: Evaluating Small Language Models Beyond Answer Accuracy in KGQA
Sep 23, 2026Eduin E. Hernandez, Sergio A. Diaz, Luis F. Garcia +2Small Language Models Knowledge Graph Question Answering
NYCU, Taiwan · National Yang Ming Chiao Tung University (NYCU), Taiwan
Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying
Sep 22, 2026Wooyoung JungBenchmark Construction Natural Language to SPARQL
Assistant Professor, Dept. of Civil and Architectural Engineering and Mechanics, Univ. of Arizona, Tucson, AZ 85719.
TCMaster: Confidence-Aware Querying and Workload-Guided Physical Design for Multi-Source Traditional Chinese Medicine Knowledge Graphs
Sep 22, 2026Zheng Chen, Yuzhu Li, Haoxuan Li +3Graph-Based Retrieval Knowledge Graphs
Tsinghua University, China · Beijing University of Chinese Medicine, China · Guangdong Provincial Laboratory of Traditional Chinese Medicine, China
Knowledge-Graph-Augmented Chronos-2 for HEC-RAS Surrogate Forecasting
Sep 18, 2026Edward Holmberg, Elias Ioup, Mahdi AbdelguerfiSurrogate Modeling Flood Forecasting
Canizaro-Livingston Gulf States Center for Environmental Informatics New Orleans, LA, USA · Center for Geospatial Sciences Naval Research Laboratory Stennis Space Center, Mississippi, USA
Initial Evaluation of Potential Bias in Coverage of Humans in Wikidata
Sep 17, 2026Clair KronkKnowledge Graphs Intersectional Fairness
Institute for Health Equity Research (IHER), Department of Population Health Science & Policy (PHSP), Icahn School of Medicine at Mount Sinai (ISMMS), New York, NY, USA · Department of Artificial Intelligence and Human Health (AIHH), Icahn School of Medicine at Mount Sinai (ISMMS), New York, NY, USA

Oct 27, 2026J/K move · Enter open · S save

Prospector: learning a compact graph traversal policy for scientific reasoning

Haiqian Yang, Markus J. Buehler

Department of Civil and Environmental Engineering Department of Mechanical Engineering Schwarzman College of Computing Massachusetts Institute of Technology Cambridge, MA, USA

LLM Reasoning with Graphs Scientific Reasoning in Language Models Knowledge Graphs

Open paper AskPDF arXiv

Scientific reasoning in specialized engineering fields depends on knowledge scattered across the literature, often proprietary and absent from frontier LLM training data. In such domains, frontier models tend to give generic answers. Knowledge graphs (KGs) can ground LLM reasoning. Because a graph is too large to provide in full, typical LLM+KG systems preselect a portion, deciding relevance before reasoning begins. Here we train a compact model, Prospector, to reason over a domain knowledge graph by traversing it step by step, seeking evidence in light of what it has already found. Prospector calls a small set of tools one at a time to progressively build its context, and answers with a chain of evidence that can be checked edge by edge against what its tools retrieved from the graph. On a knowledge graph built from the semiconductor-manufacturing literature, Prospector approaches the strongest off-the-shelf models given the same graph and tools, and it far exceeds off-the-shelf models answering closed-book or from a pre-selected portion of the graph. Although trained only on the semiconductor graph, Prospector transfers to unseen knowledge graphs from three other distinct fields: bio-inspired materials, per- and polyfluoroalkyl substances (PFAS) and materials properties. Served on a single GPU, Prospector answers faster and at a fraction of the cost of a hosted service, while keeping proprietary data on the owner's hardware. We find that the policy's latent state is indicative of its next move on both seen and unseen graphs, and modulating the latent state can steer the policy from one behavior mode to another. These results suggest a practical LLM + KG paradigm for scientific and engineering reasoning over private data, in which a compact model trained on a graph from published literature transfers its traversal to unseen graphs that stay with their owners.