面向异构业务系统的超图企业代理推理器
Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems
AI总结：
本文提出HEAR，一种基于分层超图本体的企业代理推理器，通过分层图层和超边层实现结构化多跳分析，无需重新训练LLM，在供应链任务中达到94.7%的准确率，并展示出适应性和效率。
摘要：
将大语言模型（LLMs）应用于异构企业系统受到多跳、n元推理中幻觉和失败的阻碍。现有范式（如GraphRAG、NL2SQL）缺乏复杂环境所需语义基础和可审计执行。我们引入HEAR，一种基于分层超图本体的企业代理推理器。其基图层虚拟化了具有溯源意识的数据接口，而超边层编码n元业务规则和程序协议。通过证据驱动的推理循环，HEAR动态协调本体工具进行结构化多跳分析，无需重新训练LLM。在供应链任务中，包括订单履行阻塞根本原因分析（RCA）的评估显示，HEAR达到94.7%的准确率。关键地，HEAR展示了适应性效率：利用程序超边以最小化令牌成本，同时利用拓扑探索确保复杂查询的严格正确性。通过将专有模型性能与开源权重骨干结合，并自动化手动诊断，HEAR建立了可扩展、可审计的企业智能基础。
英文摘要：
Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning. Existing paradigms (e.g., GraphRAG, NL2SQL) lack the semantic grounding and auditable execution required for these complex environments. We introduce HEAR, an enterprise agentic reasoner built on a Stratified Hypergraph Ontology. Its base Graph Layer virtualizes provenance-aware data interfaces, while the Hyperedge Layer encodes n-ary business rules and procedural protocols. Operating an evidence-driven reasoning loop, HEAR dynamically orchestrates ontology tools for structured multi-hop analysis without requiring LLM retraining. Evaluations on supply-chain tasks, including order fulfillment blockage root cause analysis (RCA), show HEAR achieves up to 94.7% accuracy. Crucially, HEAR demonstrates adaptive efficiency: utilizing procedural hyperedges to minimize token costs, while leveraging topological exploration for rigorous correctness on complex queries. By matching proprietary model performance with open-weight backbones and automating manual diagnostics, HEAR establishes a scalable, auditable foundation for enterprise intelligence.
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。
