Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· 0 citations· 20 references
TL;DR
Extensive experiments demonstrate that AgentsKG outperforms state-of-the-art training-free baselines in both extraction accuracy and structural quality, offering a robust approach to open-domain knowledge graph construction without additional training.
Abstract
Knowledge Graph Construction (KGC) is essential for transforming unstructured text into structured knowledge representations. Despite advances in Large Language Models, existing methods treat KGC as a single-pass generation task, conflating extraction, normalization, and validation within a single forward pass. This leads to hallucinated facts, polysemous conflation, and fragmented triples, particularly in open-domain settings where predefined schemas are unavailable. In this work, we propose AgentsKG, a hierarchical multi-agent framework that decouples semantic perception from structural integration. In the Semantic Perception Layer, a multi-role Verification Committee filters hallucinated and invalid assertions through majority voting, while a Contextual Profiler resolves polysemous ambiguities by enriching mentions with context-dependent semantic descriptors. In the Structural Integration Layer, a Knowledge Linker merges redundant entities and relations based on semantic profiles, and an Ontological Logic Auditor enforces logical consistency across the graph. Extensive experiments demonstrate that AgentsKG outperforms state-of-the-art training-free baselines in both extraction accuracy and structural quality, offering a robust approach to open-domain knowledge graph construction without additional training. Source code is available at https://doi.org/10.5281/zenodo.20484211
A hybrid knowledge graph generation pipeline that grounds a Large Language Model in the Wikidata multilingual Knowledge Graph while employing an agentic reflexion pattern to synthesize emerging concepts and their associated metadata to generate a comprehensive skills knowledge graph.
Emma Jouffroy, Warren Jouanneau, Marc Palyart· 0 citations
In order to enable natural language interaction with structured knowledge bases based on ontologies, widely used to represent knowledge in multiple complex domains, Knowledge Graph Question Answering (KGQA) systems are required. Large Language Models (LLMs) can play a pivotal role in this context, however they suffer from factual inaccuracies, hallucinations, and difficulties in navigating complex semantic schemas. To address these limitations, this paper proposes a novel neuro-symbolic Agentic AI framework for KGQA on real-world knowledge graph. By integrating neural reasoning capabilities of LLMs with symbolic tools within a recursive flow orchestrated by LangGraph, the system is able to identify relevant terms, validate them based on specific ontology, and generate SPARQL queries for data retrieval. To demonstrate effectiveness of this approach an experimental evaluation using a real-world smart city knowledge base, implemented in the Snap4City platform, is carried out. Results indicate that the neuro-symbolic workflows improves the accuracy of information retrieval for non-expert users compared to standalone LLM solutions.
Zahra Fereidooni, M. Fanfani, G. Pantaleo et al.· International Conference on...· 0 citations
Large Language Models (LLMs) show considerable potential for materials-science question answering. However, LLM responses may still be affected by unsupported parametric associations, while dense Retrieval-Augmented Generation (RAG) can fragment relational evidence across text chunks. Moreover, general graph-based retrieval does not necessarily preserve the hierarchical relations and factual attributes required to resolve implicit material constraints. To address these limitations, we propose MCTD-KG, a multi-source heterogeneous knowledge graph integrated with a Knowledge-Enhanced RAG framework for complex material question answering. MCTD-KG adopts a Classification–Term–Data ontology to connect disciplinary taxonomies, domain concepts, semantic relations, and empirical records from toolbooks and the scientific literature. Through LLM-assisted knowledge extraction, entity normalization, and multi-source integration, the resulting graph contains more than 530,000 entities across three layers, including 61,768 text-extracted Term-layer entities. During inference, Dual-Channel Retrieval jointly retrieves query-relevant relational paths and associated material attributes, while an explicit semantic filtering stage screens candidate evidence against the query constraints. Evaluation on an expert-validated benchmark of 1577 questions shows that the proposed framework achieves an overall accuracy of 68.48%, compared with 17.40% for the zero-shot Pure LLM, 24.79% for the best Vanilla RAG setting, and 44.96% for GraphRAG. It also achieves 45.22% accuracy on four-hop questions, compared with 39.49% for GraphRAG. These results indicate that integrating multi-source domain knowledge with relation-preserved retrieval and attribute-supported filtering provides more focused and inspectable evidence, thereby supporting more accurate complex material question answering.
Peize Li, Xi Guo, Nan Yin et al.· Electronics· 0 citations
The rapid growth of unstructured textual data necessitates automated approaches for transforming such information into structured, machine-readable knowledge. Knowledge Graphs (KGs) provide an effective framework for representing entities and their relationships; however, existing methods often suffer from fragmented pipelines, limited semantic consistency, and challenges in handling domain-specific variations. This paper presents an intelligent and scalable approach for knowledge graph construction from semantically enriched keyword-based inputs derived from a context-aware extraction process. The proposed method employs a unified pipeline comprising entity identification and ontology-based linking, context-aware relation extraction, and structured triple generation in the form of subject-predicate-object (SPO) representations. The generated triples are futher transformed into RDF format and organized into a coherent knowledge graph, followed by refinement steps to ensure semantic consistency and structural integrity. The approach is evaluated on representative datasets, including PubMed abstracts, and demonstrates improved performance in triplet extraction, entity and relation accuracy, and graph-level quality metrics such as density, clustering coefficient, and modularity. Comparative analysis with baseline methods highlights the effectiveness of the proposed approach in generating coherent and semantically enriched knowledge graphs. Additionally, the system exhibits strong scalability and computational efficiency, making it suitable for large-scale and real-world applications acreoss diverse domains. Overall, the proposed approach effectively bridges the gap between unstructured text and structured knowledge representation, enabling reliable, scalable, and high-quality knowledge graph construction.
Avinash Gondal, Sunil Wankhade· Dandao Xuebao/Journal of Bal...· 0 citations
Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts while maintaining consistency across predicted triples. Although large language models (LLMs) show remarkable reasoning capabilities in information extraction, their predictions are typically generated independently for each candidate triple and may violate fundamental relational constraints such as transitivity, symmetry, and functional uniqueness, leading to contradictory and unreliable outputs. We propose CONSISTRE, a unified consistency-aware framework for DocRE that addresses this limitation through two complementary tracks. The first operates at inference time for black-box LLMs, combining constraint-aware prompting, constraint-based verification, and iterative self-reflection to refine predictions without task-specific fine-tuning. The second injects consistency knowledge into smaller open-source models via a knowledge distillation and reinforcement learning pipeline: reasoning traces from a powerful teacher are distilled into a student via supervised fine-tuning, followed by GRPO alignment using a composite reward that jointly optimizes extraction performance and relational consistency. Together, the two tracks cover both API-accessible and locally deployable scenarios under a unified consistency formulation. Experiments on DocRED show that both tracks outperform their baselines, with the inference-time track achieving competitive F1 using off-the-shelf black-box LLMs and the training-time track substantially narrowing the gap between 7--8B open-source models and state-of-the-art proprietary LLMs at a fraction of their inference cost. Ablation studies confirm that explicit consistency modeling mitigates relational contradictions and enhances the reliability of LLM-based DocRE across both deployment paradigms.
EvoGraph-R1 is introduced, a self-evolving GraphRAG framework that reconceptualizes knowledge graphs as dynamic environments shaped through agent interactions, establishing self-evolving knowledge graphs as a fundamental paradigm across modalities.
Jiashi Lin, Changhong Jiang, Xiangru Lin et al.· 1 citation
