mlsanityData to 13 Oct 2026

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

arXiv 2604.00555 ↗First posted 1 Apr 2026cs.AI cs.CL cs.SEcited by 3

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
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.

Key facts. Cited by 3 papers in the map (data through 13 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.

Builds on

42 of 85 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks2 Feb

Other references · 41

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,376
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,221
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,492
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,657
  5. 2024Qwen2.5 Technical Reportcited by 4,840
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,196
  7. 2022Survey of Hallucination in Natural Language Generationcited by 2,068
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,815
  9. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,594
  10. 2024A Survey on LLM-as-a-Judgecited by 1,399
  11. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 758
  12. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 666
29 more
  1. 2023Augmented Language Models: a Surveycited by 403
  2. 2024Knowledge Conflicts for LLMs: A Surveycited by 277
  3. 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 255
  4. 2020Neurosymbolic AI: The 3rd Wavecited by 254
  5. 2023Efficient Guided Generation for Large Language Modelscited by 197
  6. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 194
  7. 2022GreaseLM: Graph REASoning Enhanced Language Models for Question Answeringcited by 170
  8. 2025Context Length Alone Hurts LLM Performance Despite Perfect Retrievalcited by 120
  9. 2024Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Taskscited by 105
  10. 2023Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Surveycited by 92
  11. 2023LLMs4OL: Large Language Models for Ontology Learningcited by 76
  12. 2024Can You Trust LLM Judgments? Reliability of LLM-as-a-Judgecited by 53
  13. 2024Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Modelscited by 47
  14. 2025Neuro-Symbolic AI in 2024: A Systematic Reviewcited by 37
  15. 2024GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Frameworkcited by 30
  16. 2024OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Modelscited by 23
  17. 2025Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Modelscited by 19
  18. 2025SLOT: Structuring the Output of Large Language Modelscited by 18
  19. 2025Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcementcited by 16
  20. 2023DOLCE: A Descriptive Ontology for Linguistic and Cognitive Engineeringcited by 11
  21. 2025Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcementcited by 11
  22. 2025Neural Thermodynamic Laws for Large Language Model Trainingcited by 10
  23. 2025OntoTune: Ontology-Driven Self-training for Aligning Large Language Modelscited by 8
  24. 2025Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Predictioncited by 8
  25. 2025Grounding LLM Reasoning with Knowledge Graphscited by 7
  26. 2025Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMscited by 5
  27. 2025Ontology Learning and Knowledge Graph Construction: A Comparison of Approaches and Their Impact on RAG Performancecited by 4
  28. 2025ATA: A Neuro-Symbolic Approach to Implement Autonomous and Trustworthy Agentscited by 2
  29. 2025Understanding Parametric Knowledge Injection in Retrieval-Augmented Generationcited by 1

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certificationcited by 1
  2. 2026Ontology-Amplified Distillation and Contextuality Auditing for Sovereign Enterprise Language Models: A Combined Proof-of-Mechanism and Negative-Results Method Studycited by 1
  3. 2026Narrow and Deep: An Ontology Tower as the Knowledge of an LLM Agent for an Industrial Equipment Systemcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024DANA: Domain-Aware Neurosymbolic Agents for Consistency and Accuracy
  2. 2026Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents
  3. 2023Fine-tuning Large Enterprise Language Models via Ontological Reasoning
  4. 2026Corporate Language Model (CLM): Transforming Tacit and Fragmented Enterprise Knowledge into a Sovereign, Auditable, and Executable Corporate Intelligence Layer
  5. 2025HyDRA: A Hybrid-Driven Reasoning Architecture for Verifiable Knowledge Graphs
  6. 2026Semantic Invariance in Agentic AI
  7. 2025AgentArch: A Comprehensive Benchmark to Evaluate Agent Architectures in Enterprise
  8. 2026The Semantic Training Gap: Ontology-Grounded Tool Architectures for Industrial AI Agent Systems