AI News HubLIVE
Original source2 min read

AgentNLQ: A General-Purpose Agent for Natural Language to SQL

This study presents a multi-agent method for NL2SQL that achieves 78.1% semantic accuracy on the BIRD benchmark. It leverages semantically enriched schema representation and business rules to generate accurate SQL queries, with key contributions including an optimized orchestrator, advanced schema enrichment, and demonstrated cross-domain generalization.

SourcearXiv AIAuthor: Olena Bogdanov, Yeunji Jung, Chandra Dhir, Pareekshitreddy Gaddam, Saurabh Jain, Lakshmi Tumati, Vijay Parthasarathy, Anup Shirgaonkar

[2605.19010] AgentNLQ: A General-Purpose Agent for Natural Language to SQL

[Submitted on 18 May 2026]

Title:AgentNLQ: A General-Purpose Agent for Natural Language to SQL

View a PDF of the paper titled AgentNLQ: A General-Purpose Agent for Natural Language to SQL, by Olena Bogdanov and 7 other authors

View PDF HTML (experimental)

Abstract:Natural language to SQL (NL2SQL) conversion is an important problem for researchers and enterprises due to the ubiquitous importance of relational databases in broad-ranging practical problems. Despite the rapid advancements in the capabilities of LLMs, NL2SQL has not reached parity in accuracy with human expert SQL writers, hence needing additional improvements in NL2SQL algorithms. This study presents a new multi-agent method for NL2SQL that achieves 78.1% semantic accuracy on the BIg Bench for LaRge-scale Database (BIRD) benchmark. Our method leverages a semantically enriched representation of user-provided schema, adds user-provided business rules, and produces accurate SQL queries. The main contributions of this study are (a) We designed an optimized new orchestrator in a multi-agent solution that uses LLMs to plan, orchestrate, reflect, and self-correct to generate accurate SQL queries, (b) We developed an advanced schema enrichment method that creates context-aware metadata to improve accuracy, and (c) We demonstrated the accuracy and generalizability of the method across different domains and datasets by evaluating it on the BIRD-SQL benchmark.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2605.19010 [cs.AI]

(or arXiv:2605.19010v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.19010

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Chandra Dhir [view email] [v1] Mon, 18 May 2026 18:33:15 UTC (551 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled AgentNLQ: A General-Purpose Agent for Natural Language to SQL, by Olena Bogdanov and 7 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-05

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)