# Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents

arXiv: https://arxiv.org/abs/2604.00555 · HTML: https://mlsanity.com/paper/2604.00555/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 42 of its 85 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 42)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs](https://mlsanity.com/paper/2406.15927/) (2024)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence](https://mlsanity.com/paper/2002.06177/) (2020)
- [LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks](https://mlsanity.com/paper/2402.01817/) (2024)
- [GreaseLM: Graph REASoning Enhanced Language Models for Question Answering](https://mlsanity.com/paper/2201.08860/) (2022)
- [Context Length Alone Hurts LLM Performance Despite Perfect Retrieval](https://mlsanity.com/paper/2510.05381/) (2025)
- [Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks](https://mlsanity.com/paper/2410.20266/) (2024)
- [Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey](https://mlsanity.com/paper/2311.07914/) (2023)
- [LLMs4OL: Large Language Models for Ontology Learning](https://mlsanity.com/paper/2307.16648/) (2023)
- [Can You Trust LLM Judgments? Reliability of LLM-as-a-Judge](https://mlsanity.com/paper/2412.12509/) (2024)
- [Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models](https://mlsanity.com/paper/2410.13080/) (2024)
- [Neuro-Symbolic AI in 2024: A Systematic Review](https://mlsanity.com/paper/2501.05435/) (2025)
- [GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework](https://mlsanity.com/paper/2407.10793/) (2024)
- [OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models](https://mlsanity.com/paper/2412.15235/) (2024)
- [Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models](https://mlsanity.com/paper/2508.13678/) (2025)

## Built on by (most cited first, 3 of 3)

- [Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification](https://mlsanity.com/paper/2606.04037/) (2026)
- [Ontology-Amplified Distillation and Contextuality Auditing for Sovereign Enterprise Language Models: A Combined Proof-of-Mechanism and Negative-Results Method Study](https://mlsanity.com/paper/2607.11948/) (2026)
- [Narrow and Deep: An Ontology Tower as the Knowledge of an LLM Agent for an Industrial Equipment System](https://mlsanity.com/paper/2610.11768/) (2026)

## Abstract (arXiv)

Enterprise adoption of Large Language Models (LLMs) is constrained by hallucination, domain drift, and the inability to enforce regulatory compliance at the reasoning level. We present a neurosymbolic architecture implemented within the Foundation AgenticOS (FAOS) platform that addresses these limitations through ontology-constrained neural reasoning. We introduce a three-layer ontological framework--Role, Domain, and Interaction ontologies--grounding LLM-based enterprise agents. We formalize asymmetric neurosymbolic coupling: current enterprise systems constrain agent inputs (context assembly, tool discovery, governance thresholds) but not outputs, and we propose mechanisms extending this coupling to output-side validation (response checking, reasoning verification, compliance enforcement). A controlled experiment (1,800 runs across five industries and three LLMs: Claude Sonnet 4, Qwen 2.5 72B, Gemma 4 26B) finds ontology-coupled agents significantly outperform ungrounded agents on Metric Accuracy (p < .001) and Role Consistency (p < .001) across all three models with large effect sizes (Kendall's W = .46-.64). Improvements are greatest where LLM parametric knowledge is weakest--particularly in Vietnam-localized domains, where ontology lift is 2x that of English domains. Contributions: (1) a formal three-layer enterprise ontology model; (2) a taxonomy of neurosymbolic coupling patterns; (3) ontology-constrained tool discovery via SQL-pushdown scoring; (4) a proposed framework for output-side ontological validation; (5) empirical evidence for the inverse parametric knowledge effect--ontological grounding value is inversely proportional to LLM training-data coverage of the domain; (6) cross-model replication establishing model-independence; (7) a production system serving 22 industry verticals with 650+ agents.