Structured Linked Data as a Memory Layer for Agent-Orchestrated Retrieval
On the map: Retrieval-augmented generation → Agentic RAG, agents and memory
also in 1 more
Abstract (arXiv)
Retrieval-Augmented Generation (RAG) systems typically treat documents as flat text, ignoring the structured metadata and linked relationships that knowledge graphs provide. In this paper, we investigate whether structured linked data, specifically Schema.org markup and dereferenceable entity pages served by a Linked Data Platform, can improve retrieval accuracy and answer quality in both standard and agentic RAG systems. We conduct a controlled experiment across four domains (editorial, legal, travel, e-commerce) using Vertex AI Vector Search 2.0 for retrieval and the Google Agent Development Kit (ADK) for agentic reasoning. Our experimental design tests seven conditions: three document representations (plain HTML, HTML with JSON-LD, and an enhanced agentic-optimized entity page) crossed with two retrieval modes (standard RAG and agentic RAG with multi-hop link traversal), plus an Enhanced+ condition that adds rich navigational affordances and entity interlinking. Our results reveal that while JSON-LD markup alone provides only modest improvements, our enhanced entity page format, incorporating llms.txt-style agent instructions, breadcrumbs, and neural search capabilities, achieves substantial gains: +29.6% accuracy improvement for standard RAG and +29.8% for the full agentic pipeline. The Enhanced+ variant, with richer navigational affordances, achieves the highest absolute scores (accuracy: 4.85/5, completeness: 4.55/5), though the incremental gain over the base enhanced format is not statistically significant. We release our dataset, evaluation framework, and enhanced entity page templates to support reproducibility.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 13 of its 32 references that are in the map. First posted on arXiv 11 Mar 2026.
Builds on
13 of 32 references.
References · 13
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
- 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
- 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
- 2021Improving language models by retrieving from trillions of tokenscited by 1,278
- 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
- 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
- 2020Knowledge Graphscited by 619
- 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
- 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
- 2022Multi-hop Question Answeringcited by 64
1 more
- 2023GEO: Generative Engine Optimizationcited by 53
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Novelty-Aware Agentic Retrieval: Comparing Research Contributions Through Structured Multi-Step Reasoning
- 2025Towards Open-World Retrieval-Augmented Generation on Knowledge Graph: A Multi-Agent Collaboration Framework
- 2025Retrieval Augmented Generation (RAG) for Fintech: Agentic Design and Evaluation
- 2026Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval
- 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
- 2026Agent-Enhanced Heterogeneous Graph RAG for Academic Question Answering
- 2026Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki
- 2025HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation