AgentNLQ: A General-Purpose Agent for Natural Language to SQL
arXiv cs.AI·Olena Bogdanov, Yeunji Jung, Chandra Dhir, Pareekshitreddy Gaddam, Saurabh Jain, Lakshmi Tumati, Vijay Parthasarathy, Anup Shirgaonkar
17h agoQuick Take
AgentNLQ introduces a multi-agent approach for improved natural language to SQL conversion with 78.1% accuracy.
Key Points
- Achieves 78.1% semantic accuracy on the BIRD benchmark.
- Utilizes enriched schema and business rules for better SQL generation.
- Demonstrates versatility across various domains and datasets.
📖 Reader Mode
~2 min readAbstract: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)
— Originally published at arxiv.org
More from arXiv cs.AI
See more →1d ago
FeaturedOriginal
From Prompts to Protocols: An AI Agent for Laboratory Automation
AI Summary
An AI agent integrates large language models for automating laboratory protocols, enhancing efficiency and accuracy.