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

TL;DR

This paper presents a method to integrate formal ontologies with LLMs by compiling ontologies into executable tools, enabling semantic constraint enforcement during knowledge generation and reducing manual effort.

Contribution

It introduces ontology-to-tools compilation within The World Avatar framework, enabling LLMs to adhere to formal domain constraints during knowledge creation.

Findings

Enables LLMs to follow semantic constraints during generation

Reduces manual schema and prompt engineering

Demonstrates effectiveness in chemical literature domain

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.