The paper introduces a novel LLM‑driven multi‑agent pipeline that converts relational databases into graph databases by standardizing table and column names and iteratively refining the graph schema through ETL, Analyzer, and Graph agents. The resulting graph database meets accuracy, groundedness, and faithfulness criteria and shows significant performance gains, achieving 85.6% Q&A accuracy—12.12% higher than an SQL agent on PostgreSQL—and reducing latency by roughly threefold on a BFSI dataset. This demonstrates an efficient, automated method for transforming tabular data into a more intuitive and faster‑executing graph format.
By Dinh-Khanh Pham, Quy-Anh Dang, Lam Mai Thanh, Khanh Bui, Truong-Son Hy
Structure-guided NER optimization for enterprise GraphRAG systems The post Proxy-Pointer RAG: Eliminating Wasteful Entity & Relations Extraction in Knowledge Graphs appeared first on Towards Data Science .
By Partha Sarkar
Beyond basic graph retrieval: six production-oriented architectures for combining semantic search, knowledge graphs, and LLM reasoning.
The post GraphRAG: A Practitioner's Guide to 6 Advanced Architec...
By Partha Sarkar
arXiv:2606. 06003v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) fails systematically on queries requiring structural reasoning over interconnected entities.
By Grama Chethan
arXiv:2607. 22636v1 Announce Type: new Abstract: Ontology-mediated query answering is concerned with the problem of answering queries over knowledge bases consisting of a database instance and an ontology.
By Jean-Fran\c{c}ois Baget (LIRMM, Inria, University of Montpellier, CNRS, France), Meghyn Bienvenu (Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, France), Marie-Laure Mugnier (LIRMM, Inria, University of Montpellier, CNRS, France), Micha\"el Thomazo (Inria, DIENS, ENS, PSL University, CNRS, France)
arXiv:2609.01525v1 Announce Type: cross
Abstract: A durable assumption holds that graph analytics requires a purpose-built graph engine, and that relational systems are ill-suited to connected data....
By Gene Zhang
arXiv:2602. 11745v2 Announce Type: replace Abstract: Graph models are fundamental to data analysis in domains rich with complex relationships.
By Songlin Lyu, Lujie Ban, Zihang Wu, Tianqi Luo, Jirong Liu, Ayoub Moussaid, Oskar van Rest, Heng Lin, Chenhao Ma, Nan Tang, Shipeng Qi, Yongchao Liu, Zhan Qiu, Juelu Zhang, Jiajun Zheng
The paper evaluates seven graph database engines, including Corvic AI, on a synthetic biomedical property graph with 1.02 million nodes and 5.34 million rows. It benchmarks query latency, bulk‑ingest throughput, point‑update latency, and correctness across a twenty‑query workload that covers neighborhood lookups, bounded paths, set intersections, anti‑joins, aggregation, ranking, temporal filters, full scans, and relational joins. The study finds that no single engine is universally fastest; performance depends on query shape, and the largest cost difference arises from bulk‑ingest throughput, which varies by three orders of magnitude and dominates total cost for workloads with fewer than about 10⁵ queries per data refresh.
By Donald Nguyen, Gurbinder Gill, Hadi Ahmadi, Christopher J. Rossbach
The article discusses why retrieval quality should be inherent to the system rather than dependent on how a question is phrased. It proposes reconstructing the knowledge layer by performing graph traversal on every query, incorporating bitemporal edges, and applying a two‑threshold entity resolution approach. These techniques aim to make the knowledge graph more dynamic and responsive to user queries.
By Miodrag Cekikj
arXiv:2608. 15834v1 Announce Type: new Abstract: Tool-calling LLM agents navigate unfamiliar codebases with a handful of generic primitives for listing, reading and searching files (ls, cat, grep).
By Marius Dragic, Ruben Ifrah, Alexandre Rio
The article discusses how calibrated decision models can manage high‑frequency graph decisions while large language models (LLMs) concentrate on reasoning, synthesis, and open‑ended generation. It introduces GraphRAG with TypeSafe Jev as a system‑one approach to building scalable knowledge graphs. The focus is on separating decision‑making from generative tasks to improve efficiency and reliability.
By Partha Sarkar
arXiv:2606. 17821v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in translating natural language to SQL, yet existing methods still falter on complex queries requiring multi-step, data-aware reasoning.
By Esteban Schafir, Xu Zheng, Hojat Allah Salehi, Zhuomin Chen, Mo Sha, Wei Cheng, Dongsheng Luo