@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://preview.aclanthology.org/revision-workflow/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 demonstrated exceptional performance across diverse tasks. To harness their capabilities for Text-to-SQL, we introduce R3 (Review-Rebuttal-Revision), a consensus-based multi-agent system 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 outperforms 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 outperforming GPT-3.5 on the Spider development set. We open-source our codebase at \url{https://github.com/1ring2rta/R3}."
}