OaK is presented, an ontology-as-a-kernel framework that dynamically constructs and refines task-oriented ontologies for LLM agents and shows that OaK improves standard LLM agents, strengthens evidence grounding, and boosts the reliability of multi-step reasoning.
Abstract
Large language model (LLM) agents rely heavily on knowledge encoded in model parameters or presented as unstructured context. In domain-specific tasks, this leaves important semantic connections implicit. This often results in incomplete evidence use and brittle multi-step decisions. Ontologies offer a way to externalize domain concepts and relations as machine-interpretable structures, but constructing task-usable ontologies traditionally requires substantial effort from domain experts and is difficult to scale. Automatic construction is also challenging: an ontology that appears semantically plausible may not contain the relational structures needed for actual decision making. We present OaK, an ontology-as-a-kernel framework that dynamically constructs and refines task-oriented ontologies for LLM agents. Given task requirements and training data, OaK constructs an ontology and its knowledge graph, generates task-adaptation functions for graph reasoning, and uses judge feedback to iteratively refine both. By making relevant concepts and relations explicit, the ontology grounds knowledge retrieval and multi-step decision making. We evaluate OaK on TravelPlanner, CRMArenaPro, and ToolQA. Results show that OaK improves standard LLM agents, strengthens evidence grounding, and boosts the reliability of multi-step reasoning.
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
Domain ontologies play a crucial role in organizing and integrating heterogeneous knowledge in the construction industry, particularly for the modeling and semantic representation of building codes and standards. Existing ontology construction approaches—including manual, semiautomatic, and automated methods—still rely heavily on domain experts, resulting in high development costs, subjective bias, and limited scalability. Recent large language model (LLM)-driven methods have shown promise for end-to-end ontology construction. However, their direct application to iterative ontology modeling remains challenging. LLM calls over long and dynamically evolving contexts often lead to degeneration and hallucination. Moreover, the inherent stochasticity of LLM outputs, together with the accumulation of structural errors across iterations, can progressively undermine the coherence and reliability of the constructed ontology. To address these challenges, we propose Text2Onto-Agent (T2OA), an agent-based, end-to-end ontology construction framework that formulates ontology modeling as a closed-loop reasoning process. T2OA enables an LLM-based agent to coordinate multiple diagnostic reasoning modules while interacting with a graph-based memory that persistently stores the evolving ontology. This memory provides structured and explicit contextual references across iterations, thereby reducing reliance on long-context prompts, mitigating output stochasticity, and supporting proactive error detection and correction during ontology evolution. A case study in the green building domain demonstrates the effectiveness of the proposed framework. T2OA achieves an F1-score of 0.77 for concept disambiguation, as well as prediction accuracies of 85.22% and 90.35% for parent–child and sibling relations, respectively. Furthermore, T2OA significantly outperforms baseline methods in terms of ontology completeness, highlighting its potential for constructing reliable and domain-adaptive ontologies for building codes and standards. The source code is publicly available at
https://github.com/pipiyapi/T2OA
.
Juntao He, Hainan Chen, Hai Yang et al.· Journal of construction engi...· 0 citations
Constructing formal ontologies from domain documents requires simultaneously enforcing corpus grounding, vocabulary consistency, axiom-level expressivity, and end-to-end provenance, a combination no existing automatic system delivers. We present a seven-stage graph-grounded pipeline that converts domain documents into a complete, auditable Web Ontology Language (OWL) Terminological Box (TBox) without any unconstrained generation step. Documents are first encoded as Unified Discourse-Hypergraphs (UDH) capturing entity participation and discourse dependencies; subsequent stages transform this graph evidence into a class hierarchy, typed object and datatype properties, and restriction axioms, with Large Language Model (LLM) usage restricted to narrow, graph-grounded mediation tasks. A paired Assertional Box (ABox) population procedure grounds named individuals in the induced TBox, enabling SPARQL-based functional evaluation. Every emitted term carries a full decision chain from raw source passages through each pipeline stage, making the TBox directly auditable and suitable for targeted human refinement. Evaluated on the life insurance domain using two established benchmarks and a new 100-contract corpus spanning ten product types, our pipeline achieves strong results across all evaluation dimensions, outperforming direct and multi-agent LLM baselines on competency-question (CQ) coverage (0.85 vs. 0.63 and 0.62 on one term-life contract; 0.77 vs. 0.40 and 0.44 on another contract), while also attaining high keyphrase coverage comparable to a manually-constructed reference ontology and strong performance on structured gap-and-overlap reasoning, all without any manual TBox engineering. Ontology growth analysis provides evidence consistent with vocabulary saturation at scale, demonstrating that the pipeline produces stable, reusable domain representations from large document corpora.
Maruf Ahmed Mridul, A. Talukder, O. Seneviratne· 0 citations
The results suggest that OntoExtend is useful as a drafting assistant for requirement-driven ontology extension in real world scenarios, while remaining sensitive to CQ specificity and modelling profile.
Anna Sofia Lippolis, Mohammad Javad Saeedizade, Stefan Schmid et al.· 1 citation
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.
Shilong Liu, Yongqiang Liu, Jiye Liu et al.· Proceedings of the 32nd ACM...· 0 citations
Agentic AI systems require world models that support reliable reasoning, planning, and decision-making under complex and heterogeneous conditions. Although heterogeneous graphs are natural candidates for this role, their structural design, particularly the selection of relational paths, is typically ad hoc and weakly governed from a semantic perspective, limiting robustness and interpretability. This paper proposes a semantic governance paradigm for heterogeneous world models, in which relational structures are explicitly constrained and validated at design time prior to learning. The paradigm is instantiated through Ontology-Driven Metapath Design (ODMD), which integrates ontological constraints, competency-based filtering, and lightweight predictive scoring to derive and select semantically admissible metapaths systematically. ODMD is integrated with a heterogeneous embedding pipeline, enabling the construction of governance-aware representations that combine node features, neighborhood aggregation, semantic information, and metapath-based encodings. An experimental evaluation on a multimodal heterogeneous graph shows that ontology-governed metapath design improves structural stability, semantic coherence, and robustness when compared to manual and brute-force alternatives. These results demonstrate that semantic governance provides a principled and practical foundation for agent-ready heterogeneous world models, supporting reusable, interpretable, and more reliable representations for proactive and autonomous AI systems.
S. F. Angonese, R. Galante· Annual International Compute...· 0 citations