@inproceedings{dai-etal-2026-reex,
title = "{R}e{E}x-{SQL}: Reasoning with Execution-Aware Reinforcement Learning for Text-to-{SQL}",
author = "Dai, Yaxun and
Xie, Wenxuan and
Zhuang, Xialie and
Yang, Tianyu and
Liu, Ziyi and
Yang, Haiqin and
Yang, Yiying and
Zhao, Yuhang and
Chao, Pingfu and
Jiang, Wenhao",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.35/",
pages = "824--847",
ISBN = "979-8-89176-390-6",
abstract = "Current Text-to-SQL reasoning models often lack integrated execution feedback during generation, and most existing approaches utilize feedback only for post-hoc correction. This separation not only limits real-time error correction, but may also introduce mistakes by altering otherwise correct SQL queries. To address these challenges, we present **ReEx-SQL** (Reasoning with Execution-Aware Reinforcement Learning), a Text-to-SQL framework that interacts with the SQL execution engine during decoding and dynamically adjusts reasoning based on execution feedback, thereby enabling context-sensitive query refinement and improved accuracy. ReEx-SQL achieves this through structured prompts with markup tags and a stepwise rollout strategy that incorporates execution feedback at each generation stage. For policy supervision, we design a composite reward function{---}featuring an exploration reward{---}to explicitly encourage effective interaction with the database. Furthermore, ReEx-SQL adopts a tree-based decoding strategy to facilitate exploratory reasoning and primarily aims to enhance parallel decoding efficiency. Notably, ReEx-SQL achieves 89.1{\%} accuracy on Spider and 65.3{\%} on BIRD at the 7B scale, surpassing baseline models by 2.7{\%} and 2.6{\%}, respectively. In addition, its tree-based decoding accelerates inference by 51.9{\%} compared to linear decoding during sampling."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dai-etal-2026-reex">
<titleInfo>
<title>ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaxun</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenxuan</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xialie</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiqin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiying</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pingfu</namePart>
<namePart type="family">Chao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Current Text-to-SQL reasoning models often lack integrated execution feedback during generation, and most existing approaches utilize feedback only for post-hoc correction. This separation not only limits real-time error correction, but may also introduce mistakes by altering otherwise correct SQL queries. To address these challenges, we present **ReEx-SQL** (Reasoning with Execution-Aware Reinforcement Learning), a Text-to-SQL framework that interacts with the SQL execution engine during decoding and dynamically adjusts reasoning based on execution feedback, thereby enabling context-sensitive query refinement and improved accuracy. ReEx-SQL achieves this through structured prompts with markup tags and a stepwise rollout strategy that incorporates execution feedback at each generation stage. For policy supervision, we design a composite reward function—featuring an exploration reward—to explicitly encourage effective interaction with the database. Furthermore, ReEx-SQL adopts a tree-based decoding strategy to facilitate exploratory reasoning and primarily aims to enhance parallel decoding efficiency. Notably, ReEx-SQL achieves 89.1% accuracy on Spider and 65.3% on BIRD at the 7B scale, surpassing baseline models by 2.7% and 2.6%, respectively. In addition, its tree-based decoding accelerates inference by 51.9% compared to linear decoding during sampling.</abstract>
<identifier type="citekey">dai-etal-2026-reex</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.35/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>824</start>
<end>847</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL
%A Dai, Yaxun
%A Xie, Wenxuan
%A Zhuang, Xialie
%A Yang, Tianyu
%A Liu, Ziyi
%A Yang, Haiqin
%A Yang, Yiying
%A Zhao, Yuhang
%A Chao, Pingfu
%A Jiang, Wenhao
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F dai-etal-2026-reex
%X Current Text-to-SQL reasoning models often lack integrated execution feedback during generation, and most existing approaches utilize feedback only for post-hoc correction. This separation not only limits real-time error correction, but may also introduce mistakes by altering otherwise correct SQL queries. To address these challenges, we present **ReEx-SQL** (Reasoning with Execution-Aware Reinforcement Learning), a Text-to-SQL framework that interacts with the SQL execution engine during decoding and dynamically adjusts reasoning based on execution feedback, thereby enabling context-sensitive query refinement and improved accuracy. ReEx-SQL achieves this through structured prompts with markup tags and a stepwise rollout strategy that incorporates execution feedback at each generation stage. For policy supervision, we design a composite reward function—featuring an exploration reward—to explicitly encourage effective interaction with the database. Furthermore, ReEx-SQL adopts a tree-based decoding strategy to facilitate exploratory reasoning and primarily aims to enhance parallel decoding efficiency. Notably, ReEx-SQL achieves 89.1% accuracy on Spider and 65.3% on BIRD at the 7B scale, surpassing baseline models by 2.7% and 2.6%, respectively. In addition, its tree-based decoding accelerates inference by 51.9% compared to linear decoding during sampling.
%U https://aclanthology.org/2026.acl-long.35/
%P 824-847
Markdown (Informal)
[ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL](https://aclanthology.org/2026.acl-long.35/) (Dai et al., ACL 2026)
ACL
- Yaxun Dai, Wenxuan Xie, Xialie Zhuang, Tianyu Yang, Ziyi Liu, Haiqin Yang, Yiying Yang, Yuhang Zhao, Pingfu Chao, and Wenhao Jiang. 2026. ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 824–847, San Diego, California, United States. Association for Computational Linguistics.