Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems

TL;DR

HEAR is a novel hypergraph-based enterprise reasoning system that improves multi-hop, multi-ary reasoning accuracy and efficiency without retraining LLMs, enabling scalable, auditable enterprise intelligence.

Contribution

The paper introduces HEAR, a hypergraph ontology-based reasoner that enhances reasoning in complex enterprise systems without retraining LLMs, combining accuracy, efficiency, and auditability.

Findings

Achieves up to 94.7% accuracy on supply-chain tasks.

Reduces token costs through procedural hyperedges.

Demonstrates scalable, auditable reasoning in complex environments.

Abstract

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.