Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917513848160256 |
|---|---|
| author | Wang, Ling Liu, Xin Liu, Songnan Wang, Jianan Cheng, Cheng Zhu, Yihan Li, Enyu Xiao, Yu Xie, Jiangyong Yan, Duogong Chen, Jiangyi |
| author_facet | Wang, Ling Liu, Xin Liu, Songnan Wang, Jianan Cheng, Cheng Zhu, Yihan Li, Enyu Xiao, Yu Xie, Jiangyong Yan, Duogong Chen, Jiangyi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14259 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems Wang, Ling Liu, Xin Liu, Songnan Wang, Jianan Cheng, Cheng Zhu, Yihan Li, Enyu Xiao, Yu Xie, Jiangyong Yan, Duogong Chen, Jiangyi Artificial Intelligence Computation and Language 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. |
| title | Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2605.14259 |