Abstract
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.
Abstract (translated)
企业采用大语言模型（LLMs）受到幻觉、领域漂移以及无法在推理层面执行监管合规的限制。我们提出一种在基础智能体操作系统（FAOS）平台内实现的神经符号架构，通过本体论约束的神经推理来解决这些限制。该方法引入三层本体论框架——角色、领域与交互本体论——为基于LLM的企业智能体提供形式化语义基础。我们形式化了非对称神经符号耦合的概念，其中符号本体论知识约束智能体输入（上下文组装、工具发现、治理阈值），同时提出扩展此耦合以约束智能体输出（响应验证、推理验证、合规检查）的机制。我们通过对照实验评估该架构（在金融科技、保险、医疗、越南银行业和越南保险业五个行业进行600次运行），发现本体耦合智能体在指标准确性（p < .001，W = .460）、监管合规性（p = .003，W = .318）和角色一致性（p < .001，W = .614）上显著优于无基础智能体，且在LLM参数知识最薄弱的领域——特别是越南本地化领域——提升最为显著。我们的贡献包括：（1）形式化三层企业本体论模型，（2）神经符号耦合模式分类法，（3）通过SQL下推评分实现的本体约束工具发现，（4）输出侧本体验证的提出框架，（5）反向参数知识效应的实证证据——本体基础价值与LLM训练数据覆盖领域成反比，（6）服务21个行业垂直领域、拥有650多个智能体的生产系统。
URL
https://arxiv.org/abs/2604.00555
