Saved in:
Bibliographic Details
Main Authors: Zhou, Xiaochi, Bulter, Patrick, Yang, Changxuan, Rihm, Simon D., Angkanaporn, Thitikarn, Akroyd, Jethro, Mosbach, Sebastian, Kraft, Markus
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.03439
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914304109838336
author Zhou, Xiaochi
Bulter, Patrick
Yang, Changxuan
Rihm, Simon D.
Angkanaporn, Thitikarn
Akroyd, Jethro
Mosbach, Sebastian
Kraft, Markus
author_facet Zhou, Xiaochi
Bulter, Patrick
Yang, Changxuan
Rihm, Simon D.
Angkanaporn, Thitikarn
Akroyd, Jethro
Mosbach, Sebastian
Kraft, Markus
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03439
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Ontology-to-tools compilation for executable semantic constraint enforcement in LLM agents
Zhou, Xiaochi
Bulter, Patrick
Yang, Changxuan
Rihm, Simon D.
Angkanaporn, Thitikarn
Akroyd, Jethro
Mosbach, Sebastian
Kraft, Markus
Artificial Intelligence
Information Retrieval
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.
title Ontology-to-tools compilation for executable semantic constraint enforcement in LLM agents
topic Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2602.03439