Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a neurosymbolic architecture, implemented within the Foundation AgenticOS platform, that uses a three-layer ontology (Role, Domain, Interaction) to constrain LLM reasoning in enterprise agentic systems. It formalizes asymmetric neurosymbolic coupling to constrain both agent inputs and outputs, enhancing accuracy, compliance, and role consistency. Empirical results across five industries demonstrate that ontology-coupled agents significantly outperform ungrounded agents, particularly in domains with limited LLM training data.
Hallucinating LLMs in your enterprise applications? Ontology-constrained reasoning can dramatically improve accuracy, compliance, and role consistency, especially in low-resource domains.
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. Our approach introduces a three-layer ontological framework--Role, Domain, and Interaction ontologies--that provides formal semantic grounding for LLM-based enterprise agents. We formalize the concept of asymmetric neurosymbolic coupling, wherein symbolic ontological knowledge constrains agent inputs (context assembly, tool discovery, governance thresholds) while proposing mechanisms for extending this coupling to constrain agent outputs (response validation, reasoning verification, compliance checking). We evaluate the architecture through a controlled experiment (600 runs across five industries: FinTech, Insurance, Healthcare, Vietnamese Banking, and Vietnamese Insurance), finding that ontology-coupled agents significantly outperform ungrounded agents on Metric Accuracy (p<.001, W = .460), Regulatory Compliance (p = .003, W = .318), and Role Consistency (p<.001, W = .614), with improvements greatest where LLM parametric knowledge is weakest--particularly in Vietnam-localized domains. Our contributions include: (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 that ontological grounding value is inversely proportional to LLM training data coverage of the domain, and (6) a production system serving 21 industry verticals with 650+ agents.