Text-to-SQL

Follow this topic Ask about this topic

Text-to-SQL studies how to turn natural-language questions into database queries that retrieve the intended information. Systems link questions to tables, columns, and values, then generate SQL using language models, structured intermediate plans, retrieval, or schema-aware semantic metadata. Common approaches add query decomposition, execution feedback, verification, and iterative repair; training methods include fine-tuning on curated or synthetic examples and reinforcement learning with execution-based rewards. Benchmarks such as Spider and BIRD test execution accuracy, but real deployments also expose challenges in large or changing schemas, ambiguity, multiple SQL dialects, and balancing reliability against cost and latency.

Latest papers

173 papers24 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
May 8, 2026James Petullo, Nianwen XueInference-Time Search Inference-Time Scaling
Brandeis University / Waltham, MA
PolySQL: Scaling Text-to-SQL Evaluation Across SQL Dialects via Automated Backend Isomorphism
May 8, 2026Yotam Perlitz, Elad Venezian, Corentin Royer +2Benchmark Design Text-to-SQL
1IBM Research AI · 2ETH Zürich
Anatomy of a Query: W5H Dimensions and FAR Patterns for Text-to-SQL Evaluation
May 7, 2026Vicki Stover Hertzberg, Eduardo Valverde, Joyce C. HoText-to-SQL Semantic Parsing
Emory University · Georgia Institute of Technology, Atlanta, USA
Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL
May 6, 2026Yaxun Dai, Baolin Sun, Junying Wang +6Credit Assignment in RL Text-to-SQL
Institute of Computer Science and Technology, Soochow University, China · Ant Digital Technologies, Ant Group · School of Management, University of Science and Technology of China
Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQL
May 5, 2026Le Zhou, Feng Yao, Fengcai Qiao +3Schema Linking Text-to-SQL
College of Systems Engineering, National University of Defense Technology · College of Advanced Interdisciplinary Studies, National University of Defense Technology · Institute of Automation, Chinese Academy of Sciences +1
FINER-SQL: Boosting Small Language Models for Text-to-SQL
May 5, 2026Thanh Dat Hoang, Thanh Trung Huynh, Matthias Weidlich +4Reward Modeling Small Language Models
Griffith University (Australia) · VinUniversity (Vietnam) · Humboldt-Universitat zu Berlin (Germany) +1
FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents
May 4, 2026Quang Hieu Pham, Yang He, Ping Nie +5Execution-Guided Text-to-SQL Text-to-SQL
University of Alberta · Simon Fraser University · University of Waterloo +1
EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement
May 1, 2026Jiaqian Wang, Yutao Qi, Wenjin Hou +2Text-to-SQL Relational Databases
Xidian University, Xi’an, Shaanxi 710071, China
Agent-Agnostic Evaluation of SQL Accuracy in Production Text-to-SQL Systems
Apr 30, 2026Taslim Jamal Arif, Kuldeep SinghText-to-SQL Automated Evaluation
Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding
Apr 30, 2026Smit Jivani, Sarvam Maheshwari, Sunita SarawagiText-to-SQL Grammar-Constrained Decoding
Department of Computer Science and Engineering, Indian Institute of Technology Bombay, India
EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL
Apr 29, 2026Jaehoon Lee, CheolWon Na, Suyoung Bae +4Reward Shaping Text-to-SQL
College of Computing and Informatics Sungkyunkwan University, South Korea
R $^3$ -SQL: Ranking Reward and Resampling for Text-to-SQL
Apr 28, 2026Hojae Han, Yeonseok Jeong, Seung-won Hwang +2Learning to Rank Text-to-SQL
ETRI · 2Seoul National University · 3Snowflake AI Research
Semantic Layers for Reliable LLM-Powered Data Analytics: A Paired Benchmark of Accuracy and Hallucination Across Three Frontier Models
Apr 28, 2026Michael Rumiantsau, Ivan FokeevLLM Evaluation LLM Grounding
Cube
PExA: Parallel Exploration Agent for Complex Text-to-SQL
Apr 24, 2026Tanmay Parekh, Ella Hofmann-Coyle, Shuyi Wang +3LLM Inference Efficiency Text-to-SQL
University of California Los Angeles · Bloomberg
CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems
Apr 24, 2026Tabinda Sarwar, Farhad Moghimifar, Cong Duy Vu Hoang +6Question Answering Text-to-SQL
Oracle Corporation
SemanticAgent: A Semantics-Aware Framework for Text-to-SQL Data Synthesis
Apr 23, 2026Qiang Gao, Zhenping Li, Anqi Zhuo +3Synthetic Data Generation Text-to-SQL
Center of Information Research, Academy of Military Science, Beijing 100142, China · School of Mathematics and Physics, University of Science and Technology Beijing, Beijing 100083, China
A Demonstration of SQLyzr: A Platform for Fine-Grained Text-to-SQL Evaluation and Analysis
Apr 23, 2026Sepideh Abedini, M. Tamer ÖzsuLLM Evaluation Text-to-SQL
University of Waterloo
LeGo-Code: Can Modular Curriculum Learning Advance Complex Code Generation? Insights from Text-to-SQL
Apr 20, 2026Salmane Chafik, Saad Ezzini, Ismail BerradaLLM Fine-Tuning Code Generation
Mohammed VI Polytechnic University Morocco · King Fahd University of Petroleum and Minerals Saudi Arabia
SPENCE: A Syntactic Probe for Detecting Contamination in NL2SQL Benchmarks
Apr 20, 2026Mohammadtaher Safarzadeh, Hitesh Laxmichand Patel, Afshin Orojlooyjadid +2LLM Evaluation Benchmark Contamination
Oracle AI
PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agents
Apr 19, 2026Yuan Tian, Tianyi ZhangText-to-SQL
Purdue University
FD-NL2SQL: Feedback-Driven Clinical NL2SQL that Improves with Use
Apr 17, 2026Suparno Roy Chowdhury, Tejas Anvekar, Manan Roy Choudhury +5Healthcare Text-to-SQL
Arizona State University · Mayo Clinic
Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications
Apr 16, 2026Moin Aminnaseri, Farima Fatahi Bayat, Nikita Bhutani +17Text-to-SQL Multimodal Agents
Megagon Labs
IndicDB -- Benchmarking Multilingual Text-to-SQL Capabilities in Indian Languages
Apr 15, 2026Aviral Dawar, Roshan Karanth, Vikram Goyal +1Text-to-SQL Multilingual Language Model Evaluation
Independent Researcher · BITS Pilani, Pilani, India · IIIT Delhi, New Delhi, India
SQL Query Engine: A Self-Healing LLM Pipeline for Natural Language to PostgreSQL Translation
Apr 15, 2026Muhammad Adeel IjazExecution-Guided Text-to-SQL Text-to-SQL
ROSE: An Intent-Centered Evaluation Metric for NL2SQL
Apr 14, 2026Wenqi Pei, Shizheng Hou, Boyan Li +3Text-to-SQL Automated Evaluation
The Hong Kong University of Science and Technology (Guangzhou) · National University of Singapore
NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions
Apr 13, 2026Shizheng Hou, Wenqi Pei, Nuo Chen +3Text-to-SQL Benchmark Design
National University of Singapore · Zhejiang University
ClinQueryAgent: A Conversational Agent for Population Health Management
Apr 13, 2026Joseph S. Boyle, Anthony Dranfield, Mike O'Neil +2Healthcare LLM Agents
Canon Medical Research Europe · Queen Mary University of London · Nottingham and Nottinghamshire ICB, NHS England +1
Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method
Apr 12, 2026Taehee Kim, Seungbin Yang, Jihwan Kim +1Table Retrieval Adaptive Retrieval
KAIST AI · Letsur
AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views
Apr 8, 2026Minh Tam Pham, Trinh Pham, Tong Chen +3Text-to-SQL Multi-Agent LLM Systems
Griffith University (Australia) · The University of Queensland (Australia)
SQLStructEval: Structural Evaluation of LLM Text-to-SQL Generation
Apr 8, 2026Yixi Zhou, Fan Zhang, Zhiqiao Guo +4Text-to-SQL Evaluation Text-to-SQL
Hong Kong Baptist University · ShanghaiTech University · The University of Tokyo +2

May 8, 2026J/K move · Enter open · S save

CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation

James Petullo, Nianwen Xue

Brandeis University / Waltham, MA

Inference-Time Search Inference-Time Scaling Text-to-SQL Inference-Time Compute Allocation

Open paper AskPDF arXiv

While recent advancements in inference-time learning have improved LLM reasoning on Text-to-SQL tasks, current solutions still struggle to perform well on the most challenging tasks in the Bird-Bench (BIRD) benchmark. This is due to inadequate solution space exploration, which is necessary to uncover promising candidate queries that can be further refined to produce the correct output. To address this challenge, we introduce CA-SQL, a novel Text-to-SQL pipeline that utilizes the estimated difficulty of a task to dynamically scale the breadth of the exploration for generating solution candidates. In addition, we use a custom prompt seeding method, based on principles of evolutionary search, to further elicit exploratory behavior from the base LLM and a novel voting method to select the best candidate solution at the end of the search. Experiments demonstrate that our solution achieves a state-of-the-art score of 51.72% on the "challenging" tier of BIRD development set problems, using only GPT-4o-mini, out-performing other in-context learning approaches, even those that leverage larger models. Overall, our method attains a competitive 61.06% execution accuracy and 68.77% Soft F1 score on the BIRD development dataset.