@inproceedings{xia-etal-2025-r3,
title = "$R^3$: ``This is My {SQL}, Are You With Me?'' A Consensus-Based Multi-Agent System for Text-to-{SQL} Tasks",
author = "Xia, Hanchen and
Jiang, Feng and
Deng, Naihao and
Wang, Cunxiang and
Zhao, Guojiang and
Mihalcea, Rada and
Zhang, Yue",
editor = "Chang, Shuaichen and
Hulsebos, Madelon and
Liu, Qian and
Chen, Wenhu and
Sun, Huan",
booktitle = "Proceedings of the 4th Table Representation Learning Workshop",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.trl-1.4/",
doi = "10.18653/v1/2025.trl-1.4",
pages = "34--46",
ISBN = "979-8-89176-268-8",
abstract = "Large Language Models (LLMs) have demon- strated exceptional performance across diverse tasks. To harness their capabilities for Text- to-SQL, we introduce R3 (Review-Rebuttal- Revision), a consensus-based multi-agent sys- tem for Text-to-SQL tasks. R3 achieves the new state-of-the-art performance of 89.9 on the Spider test set. In the meantime, R3 achieves 61.80 on the Bird development set. R3 out- performs existing single-LLM and multi-agent Text-to-SQL systems by 1.3{\%} to 8.1{\%} on Spi- der and Bird, respectively. Surprisingly, we find that for Llama-3-8B, R3 outperforms chain-of- thought prompting by over 20{\%}, even outper- forming GPT-3.5 on the Spider development set. We open-source our codebase at https: //github.com/1ring2rta/R3."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xia-etal-2025-r3">
<titleInfo>
<title>R³: “This is My SQL, Are You With Me?” A Consensus-Based Multi-Agent System for Text-to-SQL Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanchen</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naihao</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cunxiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guojiang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Table Representation Learning Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuaichen</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madelon</namePart>
<namePart type="family">Hulsebos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-268-8</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have demon- strated exceptional performance across diverse tasks. To harness their capabilities for Text- to-SQL, we introduce R3 (Review-Rebuttal- Revision), a consensus-based multi-agent sys- tem for Text-to-SQL tasks. R3 achieves the new state-of-the-art performance of 89.9 on the Spider test set. In the meantime, R3 achieves 61.80 on the Bird development set. R3 out- performs existing single-LLM and multi-agent Text-to-SQL systems by 1.3% to 8.1% on Spi- der and Bird, respectively. Surprisingly, we find that for Llama-3-8B, R3 outperforms chain-of- thought prompting by over 20%, even outper- forming GPT-3.5 on the Spider development set. We open-source our codebase at https: //github.com/1ring2rta/R3.</abstract>
<identifier type="citekey">xia-etal-2025-r3</identifier>
<identifier type="doi">10.18653/v1/2025.trl-1.4</identifier>
<location>
<url>https://aclanthology.org/2025.trl-1.4/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>34</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T R³: “This is My SQL, Are You With Me?” A Consensus-Based Multi-Agent System for Text-to-SQL Tasks
%A Xia, Hanchen
%A Jiang, Feng
%A Deng, Naihao
%A Wang, Cunxiang
%A Zhao, Guojiang
%A Mihalcea, Rada
%A Zhang, Yue
%Y Chang, Shuaichen
%Y Hulsebos, Madelon
%Y Liu, Qian
%Y Chen, Wenhu
%Y Sun, Huan
%S Proceedings of the 4th Table Representation Learning Workshop
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-268-8
%F xia-etal-2025-r3
%X Large Language Models (LLMs) have demon- strated exceptional performance across diverse tasks. To harness their capabilities for Text- to-SQL, we introduce R3 (Review-Rebuttal- Revision), a consensus-based multi-agent sys- tem for Text-to-SQL tasks. R3 achieves the new state-of-the-art performance of 89.9 on the Spider test set. In the meantime, R3 achieves 61.80 on the Bird development set. R3 out- performs existing single-LLM and multi-agent Text-to-SQL systems by 1.3% to 8.1% on Spi- der and Bird, respectively. Surprisingly, we find that for Llama-3-8B, R3 outperforms chain-of- thought prompting by over 20%, even outper- forming GPT-3.5 on the Spider development set. We open-source our codebase at https: //github.com/1ring2rta/R3.
%R 10.18653/v1/2025.trl-1.4
%U https://aclanthology.org/2025.trl-1.4/
%U https://doi.org/10.18653/v1/2025.trl-1.4
%P 34-46
Markdown (Informal)
[R3: “This is My SQL, Are You With Me?” A Consensus-Based Multi-Agent System for Text-to-SQL Tasks](https://aclanthology.org/2025.trl-1.4/) (Xia et al., TRL 2025)
ACL
- Hanchen Xia, Feng Jiang, Naihao Deng, Cunxiang Wang, Guojiang Zhao, Rada Mihalcea, and Yue Zhang. 2025. R3: “This is My SQL, Are You With Me?” A Consensus-Based Multi-Agent System for Text-to-SQL Tasks. In Proceedings of the 4th Table Representation Learning Workshop, pages 34–46, Vienna, Austria. Association for Computational Linguistics.