mlsanityData to 7 Oct 2026

Beyond Vector Similarity: A Structural Analysis of Graph-Augmented Retrieval for Industrial Knowledge Graphs

arXiv 2606.06003 ↗First posted 4 Jun 2026cs.AIcited by 0

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) fails systematically on queries requiring structural reasoning over interconnected entities. We compare eight retrieval architectures for aerospace supply chain intelligence, progressing from text retrieval through graph traversal to graph computation. Using a 46-node knowledge graph with 64 typed edges, we evaluate 23 queries across 10 intent categories and demonstrate that five query classes are structurally unreachable for vector retrieval. Our central finding is the operator vocabulary thesis: the barrier to LLM-based graph reasoning is not model intelligence but the computational operators available as tools. An LLM Query Planner with 9 typed traversal primitives outperforms bespoke handlers (F1 = 0.632 vs. 0.472) while generalizing to unseen queries. Adding 6 graph computation tools, the LLM selectively adopts them for exactly the query categories where traversal fails. We also identify a measurement gap: entity-level F1 systematically underscores structural queries where comprehensive answers are correct.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 14 of its 20 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

14 of 20 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledge15 Oct
  2. 2024LightRAG: Simple and Fast Retrieval-Augmented Generation8 Oct
  3. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  4. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering12 Feb

Other references · 10

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  4. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
  5. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  6. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  7. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 223
  8. 2024Corrective Retrieval Augmented Generationcited by 187
  9. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 138
  10. 2020KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Basecited by 76

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Practical GraphRAG: Efficient Knowledge Graph Construction and Hybrid Retrieval at Scale
  2. 2026Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations
  3. 2026VDGR-RAG: Vectors, Directories, Graphs, and Reflection Are All You Need for Unified Reasoning over Hierarchical Enterprise Knowledge
  4. 2025Scalable and Explainable Enterprise Knowledge Discovery Using Graph-Centric Hybrid Retrieval
  5. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
  6. 2024LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration
  7. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
  8. 2025GRAIL:Learning to Interact with Large Knowledge Graphs for Retrieval Augmented Reasoning