用知识图谱约束大模型推理，提升企业AI代理的准确性和合规性。
Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents
- 构建角色、领域、交互三层知识图谱，约束大模型输入与输出
- 实验显示准确率和角色一致性显著提升，越南本地化场景效果翻倍
- 适合需要强合规、跨行业落地的企业级AI系统开发者
企业采用大语言模型受限于幻觉、领域漂移及推理层面的合规难问题。本文在Foundation AgenticOS平台中提出一种神经符号架构，通过知识图谱约束实现企业级AI代理的可靠推理。构建角色、领域、交互三层本体框架，形式化非对称神经符号耦合机制：现有系统仅约束输入，本文提出扩展至输出侧验证（响应检查、推理验证、合规执行）。1,800次跨五行业、三模型（Claude Sonnet 4、Qwen 2.5 72B、Gemma 4 26B）的对照实验表明，知识图谱耦合代理在指标准确率（p < .001）和角色一致性（p < .001）上显著优于无约束代理，效应量较大（Kendall's W = .46-.64）。当大模型参数知识最弱时改进最大——越南本地化领域效果是英文领域的2倍。贡献包括：(1) 三层次企业本体模型；(2) 神经符号耦合模式分类；(3) 基于SQL下推评分的本体约束工具发现；(4) 输出侧本体验证框架；(5) 逆参数知识效应实证——本体接地价值与模型训练数据覆盖度成反比；(6) 多模型复现证明独立性；(7) 支持22个行业垂直领域、650+代理的生产系统。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。