企业智能体系统中的本体约束神经推理：一种面向领域 grounded AI 智能体的神经符号架构
Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents
AI总结：
本文提出了一种神经符号架构，通过本体约束神经推理解决企业大语言模型在幻觉、领域漂移和无法在推理层面强制执行监管合规性方面的限制，展示了该架构在提升智能体的指标准确性和角色一致性方面的显著效果。
摘要：
企业采用大语言模型（LLMs）受到幻觉、领域漂移和无法在推理层面强制执行监管合规性的限制。我们提出了一种在基础智能体操作系统（FAOS）平台中实现的神经符号架构，通过本体约束神经推理解决这些限制。我们引入了一个三层本体框架——角色、领域和交互本体——以地面化基于LLM的企业智能体。我们正式化了不对称的神经符号耦合：当前企业系统约束智能体输入（上下文组装、工具发现、治理阈值），但不约束输出，我们提出机制扩展这种耦合到输出侧验证（响应检查、推理验证、合规性强制）。一个受控实验（1,800次运行，覆盖五个行业和三个LLM：Claude Sonnet 4、Qwen 2.5 72B、Gemma 4 26B）发现本体耦合的智能体在所有三个模型中在指标准确性和角色一致性上显著优于无地面化智能体（p < .001），具有较大的效应量（Kendall's W = .46-.64）。改进最大出现在LLM参数化知识最弱的地方——特别是越南本地化领域，其中本体提升是英语领域的2倍。贡献：（1）一个正式的三层企业本体模型；（2）神经符号耦合模式的分类学；（3）通过SQL推导评分进行本体约束的工具发现；（4）提出的一种用于输出侧本体验证的框架；（5）关于参数化知识效应的实证证据——本体地面化价值与LLM训练数据覆盖领域成反比；（6）跨模型复制，确立模型独立性；（7）一个服务于22个行业垂直领域的生产系统，拥有650多个智能体。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
