Ontology-to-tools compilation for executable semantic constraint enforcement in LLM agents

• URL: http://arxiv.org/abs/2602.03439v1
• Date: Tue, 03 Feb 2026 12:03:26 GMT
• Title: Ontology-to-tools compilation for executable semantic constraint enforcement in LLM agents
• Authors: Xiaochi Zhou, Patrick Bulter, Changxuan Yang, Simon D. Rihm, Thitikarn Angkanaporn, Jethro Akroyd, Sebastian Mosbach, Markus Kraft,
• Abstract summary: We present a proof-of-principle mechanism for coupling large language models (LLMs) with formal domain knowledge semantics.<n>Ontological specifications are compiled into executable tool tools that LLM-based agents must use to create and modify knowledge graph instances.<n>We show how executable ontological semantics guide LLM interfaces and reduce manual schema and prompt engineering, establishing a general paradigm for embedding formal knowledge into generative systems.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce ontology-to-tools compilation as a proof-of-principle mechanism for coupling large language models (LLMs) with formal domain knowledge. Within The World Avatar (TWA), ontological specifications are compiled into executable tool interfaces that LLM-based agents must use to create and modify knowledge graph instances, enforcing semantic constraints during generation rather than through post-hoc validation. Extending TWA's semantic agent composition framework, the Model Context Protocol (MCP) and associated agents are integral components of the knowledge graph ecosystem, enabling structured interaction between generative models, symbolic constraints, and external resources. An agent-based workflow translates ontologies into ontology-aware tools and iteratively applies them to extract, validate, and repair structured knowledge from unstructured scientific text. Using metal-organic polyhedra synthesis literature as an illustrative case, we show how executable ontological semantics can guide LLM behaviour and reduce manual schema and prompt engineering, establishing a general paradigm for embedding formal knowledge into generative systems.

Related papers

• Ontology-aligned structuring and reuse of multimodal materials data and workflows towards automatic reproduction [1.4658400971135652]
  Existing text-mining approaches are insufficient to extract complete computational with associated parameters.<n>A large language model (LLM)-assisted framework is introduced for the automated extraction and structuring of computational density from the literature.<n>The framework provides a foundation for organizing and contextualizing published results in a semantically interoperable form, thereby improving transparency and reusability of computational materials data.
  arXiv  Detail & Related papers  (2026-01-18T20:51:23Z)
• Monadic Context Engineering [59.95390010097654]
  This paper introduces Monadic Context Engineering (MCE) to provide a formal foundation for agent design.<n>We demonstrate how Monads enable robust composition, how Applicatives provide a principled structure for parallel execution, and crucially, how Monad Transformers allow for the systematic composition of these capabilities.<n>This layered approach enables developers to construct complex, resilient, and efficient AI agents from simple, independently verifiable components.
  arXiv  Detail & Related papers  (2025-12-27T01:52:06Z)
• Integrating Ontologies with Large Language Models for Enhanced Control Systems in Chemical Engineering [1.0674471416489186]
  This work presents an ontology-integrated large language model (LLM) framework for chemical engineering that unites structured domain knowledge with generative reasoning.<n>The proposed pipeline aligns model training and inference with the COPE ontology through a sequence of data acquisition, semantic preprocessing, information extraction, and ontology mapping steps.<n>This integration of symbolic structure and neural generation provides a transparent, auditable approach for applying LLMs to process control, safety analysis, and other critical engineering contexts.
  arXiv  Detail & Related papers  (2025-10-30T18:04:20Z)
• Executable Ontologies: Synthesizing Event Semantics with Dataflow Architecture [51.56484100374058]
  We demonstrate that integrating semantic event semantics with a dataflow architecture addresses the limitations of traditional Business Process Management systems.<n>The boldsea-engine's architecture interprets semantic models as executable algorithms without compilation.<n>It enables the modification of event models at runtime ensures transparency, and seamlessly merges data and business logic within a unified semantic framework.
  arXiv  Detail & Related papers  (2025-09-11T18:12:46Z)
• Data Dependency-Aware Code Generation from Enhanced UML Sequence Diagrams [54.528185120850274]
  We propose a novel step-by-step code generation framework named API2Dep.<n>First, we introduce an enhanced Unified Modeling Language (UML) API diagram tailored for service-oriented architectures.<n>Second, recognizing the critical role of data flow, we introduce a dedicated data dependency inference task.
  arXiv  Detail & Related papers  (2025-08-05T12:28:23Z)
• Do We Really Need GNNs with Explicit Structural Modeling? MLPs Suffice for Language Model Representations [50.45261187796993]
  Graph Neural Networks (GNNs) fail to fully utilize structural information, whereas Multi-Layer Perceptrons (MLPs) exhibit a surprising ability in structure-aware tasks.<n>This paper introduces a comprehensive probing framework from an information-theoretic perspective.
  arXiv  Detail & Related papers  (2025-06-26T18:10:28Z)
• Large Language Models are Good Relational Learners [55.40941576497973]
  We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
  arXiv  Detail & Related papers  (2025-06-06T04:07:55Z)
• LLMs4SchemaDiscovery: A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models [0.22470290096767]
  Traditional schema mining relies on semi-structured data, limiting scalability.<n>This paper introduces schema-miner, a novel tool that combines large language models with human feedback to automate and refine schema extraction.
  arXiv  Detail & Related papers  (2025-04-01T13:03:33Z)
• Interpreting token compositionality in LLMs: A robustness analysis [10.777646083061395]
  Constituent-Aware Pooling (CAP) is a methodology designed to analyse how large language models process linguistic structures.<n>CAP intervenes in model activations through constituent-based pooling at various model levels.<n>Our findings highlight fundamental limitations in current transformer architectures regarding compositional semantics processing and model interpretability.
  arXiv  Detail & Related papers  (2024-10-16T18:10:50Z)
• A process algebraic framework for multi-agent dynamic epistemic systems [55.2480439325792]
  We propose a unifying framework for modeling and analyzing multi-agent, knowledge-based, dynamic systems. On the modeling side, we propose a process algebraic, agent-oriented specification language that makes such a framework easy to use for practical purposes.
  arXiv  Detail & Related papers  (2024-07-24T08:35:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.