Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems
cs.AI, cs.CL
Submitted: 2026-05-14
Updated: 2026-09-07
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning.
Terminology
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.
Sources
- Large Language Models Hallucination: A Comprehensive Survey
- When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
- AgentSM: Semantic Memory for Agentic Text-to-SQL
- Dingtalk DeepResearch: A Unified Multi Agent Framework for Adaptive Intelligence in Enterprise Environments
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Benchmarking Deep Search over Heterogeneous Enterprise Data
- A comprehensive taxonomy of hallucinations in Large Language Models
- Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation
- A Survey on LLM-as-a-Judge
- Retrieval-Augmented Generation with Graphs (GraphRAG)
- Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
- MemGPT: Towards LLMs as Operating Systems
- Agent Drift: Quantifying Behavioral Degradation in Multi-Agent LLM Systems Over Extended Interactions
- CSR-RAG: An Efficient Retrieval System for Text-to-SQL on the Enterprise Scale
- MIRIX: Multi-Agent Memory System for LLM-Based Agents
- HypKG: Hypergraph-based Knowledge Graph Contextualization for Precision Healthcare
- Graph-based Agent Memory: Taxonomy, Techniques, and Applications
- TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning
- The KnowWhereGraph: A Large-Scale Geo-Knowledge Graph for Interdisciplinary Knowledge Discovery and Geo-Enrichment
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection