Elamur Research⌕
☰
home / papers / 2026 / Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Tasks

Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Tasks

Paper · 2026 · Yihan Wang, Peiyu Liu, Runyu Chen et al.

Summary

Text-to-SQL research has produced many strong methods, but each solves a narrow sub-problem and comes with its own data formats and interfaces. This makes them hard to combine for real-world queries, where several difficulties usually occur together. The authors present Squrve, an open-source framework with four modules for data, actors, tasks and execution. It converts benchmarks and private datasets into one shared format and splits large schemas into column-level files for retrieval. It also gives existing systems a common calling interface. The Text-to-SQL process is broken into seven atomic "actors", each taken from a published method. Actors can be chained sequentially (Pipeline) or run in parallel and merged (Tree). On Spider and Bird with a Qwen-3 backbone, Squrve matches or slightly exceeds the original results of five reproduced baselines. Two composed workflows beat every individual method. The work matters because it offers a practical route from separate academic techniques to deployable, mix-and-match Text-to-SQL pipelines.

Key points

  • The seven atomic actors are Reduce, Parse, Generate, Decompose, Scale, Optimize and Select. They draw on LinkAlign, RSL-SQL, DIN-SQL, CHESS, MAC-SQL, CHASE-SQL, OpenSearch and MCS-SQL. Pipeline and Tree compositions can be nested recursively.
  • The data module maintains over 200 chain-of-thought exemplars for retrieval-based prompting. It also splits centralized schemas into per-column files so that relevant parts can be retrieved via RAG.
  • Reproduced baselines track their original results closely. For example, DIN-SQL scores 82.5 vs. 81.7 EX on Spider-dev and 60.1 vs. 59.4 on Bird-dev.
  • Ensemble-2 combines RSLSQLBiDirParser, MACSQLDecompose, ChessScaler, CHESSSelector and LinkAlignOptimizer. It reaches 90.8 EX on Spider-dev and 70.0 on Bird-dev, compared with 87.3 and 68.0 for the best reproduced single method. Ensemble-1 scores 88.7 and 67.3.
  • Running schema linkers in parallel raises recall. LinkAlign, RSL-SQL and DIN-SQL together reach 93.1 recall on Bird-dev, while the best single linker reaches 82.4. Precision drops, and two-actor combinations give the best trade-off between gains and computational overhead.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Renmin University of ChinaBeijing · China114 works · 16,118 citations🎓Zhejiang University of TechnologyHangzhou · China6 works · 98 citations🎓University of International Business and EconomicsBeijing · China7 works · 37 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Networks and Communications · 64 works

🧭 Topics 2Research subjects and languages the work is about.Semantic parsing & meaning representation · 185 worksCode & programming languages · 129 works

Cite

Cite as Yihan Wang, Peiyu Liu, Runyu Chen, Jiaxing Pu and Wei Xu. 2026. Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Tasks. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-demo.16

@inproceedings{wang2026squrve,
  title = {{Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Tasks}},
  author = {Yihan Wang, Peiyu Liu, Runyu Chen, Jiaxing Pu and Wei Xu},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-demo.16},
  url = {https://doi.org/10.18653/v1/2026.acl-demo.16}
}

References

41 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Zhenbiao Cao, Yuanlei Zheng, Zhihao Fan, Xiaojin Zhang, Wei Chen, and Xiang Bai. 2024. Rsl-sql: Robust schema linking in text-to-sql generation. arXiv preprint arXiv:2411.00073. — [arXiv:2411.00073](https://arxiv.org/abs/2411.00073) find
  2. DongHyun Choi, Min C Shin, EungGyun Kim, and Dong Ryeol Shin. 2021. Ryansql: Recursively applying sketch-based slot fillings for complex text-to-sql in cross-domain databases.
  3. Michael Deng, Akshara Ramachandran, Cheng Xu, Lyuzhou Hu, Zhoujun Yao, Anindya Datta, and Heng Zhang. 2025. Reforce: A text-to-sql agent with self-refinement, format restriction, and column exploration. In ICLR 2025 The VerifAI Workshop. find
  4. Xiang Deng, Ahmed Hassan Awadallah, Christopher Meek, Oleksandr Polozov, Huan Sun, and Matthew Richardson. 2021. Structure-grounded pretraining for text-to-sql. In North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
  5. Dawei Gao, Haibin Wang, Yaliang Li, Xiuyu Sun, Yue Qian, Bolin Ding, and Jingren Zhou. 2024. Text-to-sql empowered by large language models: A benchmark evaluation. In International Conference on Very Large Data Bases.
  6. Zijin Hong, Zheng Yuan, Qinggang Zhang, Hao Chen, Junnan Dong, Feiran Huang, and Xiao Huang. 2025. Next-generation database interfaces: A survey of llm-based text-to-sql. arXiv preprint arXiv:2406.08426. — [arXiv:2406.08426](https://arxiv.org/abs/2406.08426) find
  7. Binyuan Hui, Xiang Shi, Ruiying Geng, Binhua Li, Yongbin Li, Jian Sun, and Xiaodan Zhu. 2021. Improving text-to-sql with schema dependency learning. find
  8. Siqi Kou, Lanxiang Hu, Zhezhi He, Zhijie Deng, and Hao Zhang. 2024. Cllms: Consistency large language models. In International Conference on Machine Learning. find
  9. Dongjun Lee, Choongwon Park, Jaehyuk Kim, and Heesoo Park. 2024. Mcs-sql: Leveraging multiple prompts and multiple-choice selection for text-to-sql generation. arXiv preprint arXiv:2405.07467.
  10. Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin SU, Zhaoqing SUO, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, and 1 others. 2025. Spider 2.0: Evaluating language models on real-world enterprise text-to-sql workflows. In International Conference on Learning Representations. find
  11. Fei Li and HV Jagadish. 2014. Constructing an interactive natural language interface for relational databases. In International Conference on Very Large Data Bases. find
  12. Haoyang Li, Jing Zhang, Cuiping Li, and Hong Chen. 2023a. Resdsql: Decoupling schema linking and skeleton parsing for text-to-sql. In Conference on Artificial Intelligence.
  13. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
  14. Xuemei Dong, Chao Zhang, Yuhang Ge, Yuren Mao, Yunjun Gao, Jinshu Lin, Dongfang Lou, and 1 others. 2023. C3: Zero-shot text-to-sql with chatgpt. find
  15. Yujian Gan, Xinyun Chen, Qiuping Huang, Matthew Purver, John R Woodward, Jinxia Xie, and Peng-sheng Huang. 2021a. Towards robustness of text-to-sql models against synonym substitution. In Association for Computational Linguistics and International Joint Conference on Natural Language Processing.
  16. Yujian Gan, Xinyun Chen, and Matthew Purver. 2021b. Exploring underexplored limitations of cross-domain text-to-sql generalization. In Empirical Methods in Natural Language Processing (EMNLP).
  17. Jinyang Li, Binyuan Hui, Reynold Cheng, Bowen Qin, Chenhao Ma, Nan Huo, Fei Huang, Wenyu Du, Luo Si, and Yongbin Li. 2023b. Graphix-t5: Mixing pre-trained transformers with graph-aware layers for text-to-sql parsing. In Conference on Artificial Intelligence. find
  18. Jinyang Li, Binyuan Hui, Ge Qu, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Ruiying Geng, Nan Huo, and 1 others. 2023c. Can llm already serve as a database interface? a big bench for large-scale database grounded text-to-sqls. In Advances in Neural Information Processing Systems.
  19. Xinyu Liu, Shuyu Shen, Boyan Li, Peixian Ma, Runzhi Jiang, Yuxin Zhang, Ju Fan, Guoliang Li, Nan Tang, and Yuyu Luo. 2024. A survey of nl2sql with large language models: Where are we, and where are we going? arXiv preprint arXiv:2408.05109. — [arXiv:2408.05109](https://arxiv.org/abs/2408.05109) find
  20. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. find
  21. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.
  22. Xinyu Pi, Bing Wang, Yan Gao, Jiawei Guo, Zhoujun Li, and Jian-Guang Lou. 2022. Towards robustness of text-to-sql models against natural and realistic adversarial table perturbation. In Association for Computational Linguistics. find
  23. Mohammadreza Pourreza, Haiyang Li, Ruoxi Sun, Yeounoh Chung, Shayan Talaei, Gaurav T Kakkar, Yu Gan, Amin Saberi, Fatma Ozcan, and Sercan O Arik. 2025. Chase-sql: Multi-path reasoning and preference optimized candidate selection in text-to-sql. In International Conference on Learning Representations… find
  24. Mohammadreza Pourreza and Davood Rafiei. 2023. Din-sql: Decomposed in-context learning of text-to-sql with self-correction. In Advances in Neural Information Processing Systems.
  25. Liang Shi, Zhengju Tang, Nan Zhang, Xiaotong Zhang, and Zhi Yang. 2025. A survey on employing large language models for text-to-sql tasks. ACM Computing Surveys, 58(2):1–37. find
  26. Shayan Talaei, Mohammadreza Pourreza, Yu-Chen Chang, Azalia Mirhoseini, and Amin Saberi. 2024. Chess: Contextual harnessing for efficient sql synthesis. arXiv preprint arXiv:2405.16755. — [arXiv:2405.16755](https://arxiv.org/abs/2405.16755) find
  27. Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, Linzheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xipeng Sun, and 1 others. 2024. Mac-sql: A multi-agent collaborative framework for text-to-sql. In International Conference on Computational Linguistics.
  28. Lihan Wang, Bowen Qin, Binyuan Hui, Bowen Li, Min Yang, Bailin Wang, Binhua Li, Jian Sun, Fei Huang, Luo Si, and Yongbin Li. 2022a. Proton: Probing schema linking information from pre-trained language models for text-to-sql parsing. In Conference on Knowledge Discovery and Data Mining (KDD). find
  29. Tianshu Wang, Hongyu Lin, Xianpei Han, Le Sun, Xiaoyang Chen, Hao Wang, and Zhenyu Zeng. 2023. Dbcopilot: Scaling natural language querying to massive databases. arXiv preprint arXiv:2312.03463. — [arXiv:2312.03463](https://arxiv.org/abs/2312.03463) find
  30. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022b. Self-consistency improves chain of thought reasoning in language models. In ICLR.
  31. Yihan Wang, Peiyu Liu, and Xin Yang. 2025. Linkalign: Scalable schema linking for real-world large-scale multi-database text-to-sql. arXiv preprint arXiv:2503.18596. find
  32. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In NeurIPS.
  33. Xiangjin Xie, Guangwei Xu, Lingyan Zhao, and Ruijie Guo. 2025. Opensearch-sql: Enhancing text-to-sql with dynamic few-shot and consistency alignment. Proceedings of the ACM on Management of Data, 3(3):1–24. find
  34. Silei Xu, Sina Semnani, Giovanni Campagna, and Monica Lam. 2020. Autoqa: From databases to qa semantic parsers with only synthetic training data. In Empirical Methods in Natural Language Processing (EMNLP). find
  35. Siqiao Xue, Caigao Jiang, Wenhui Shi, Fangyin Cheng, Keting Chen, Hongjun Yang, Zhiping Zhang, Jianshan He, Hongyang Zhang, Ganglin Wei, and 1 others. 2024. Db-gpt: Empowering database interactions with private large language models. find
  36. Pengcheng Yin, Graham Neubig, Wen-tau Yih, and Sebastian Riedel. 2020. Tabert: Pretraining for joint understanding of textual and tabular data.
  37. Tao Yu, Shuaichen Chang, Jiaqi Wang, Ming Dong, Linyong Pan, Henghui Zhu, Abishek Li, Wenting Lan, Shuaigi Zhang, Jiarong Jiang, and 1 others. 2023. Dr. spider: A diagnostic evaluation benchmark towards text-to-sql robustness. In International Conference on Learning Representations (ICLR). find
  38. Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, and 1 others. 2018. Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. In Empirical Methods in Natural Language Proce…
  39. Bin Zhang, Yuxiao Ye, Guosheng Du, Xiaoxu Hu, Zhishuai Li, Sun Yang, Haoxuan Chi, Rui Liu, Zichen Zhao, Zhi Li, and 1 others. 2024. Benchmarking the text-to-sql capability of large language models: A comprehensive evaluation. arXiv preprint arXiv:2403.02951. — [arXiv:2403.02951](https://arxiv.org/abs/2403.02951) find
  40. Tianyi Zhang, Tao Yu, Tatsunori B Hashimoto, Mike Lewis, Wen-tau Yih, Daniel Fried, and Sida I Wang. 2023. Coder reviewer reranking for code generation. In International Conference on Machine Learning. find
  41. Ruiqi Zhong, Bing Wang, Yan Gao, Jiaqi Guo, Zhan Li, and Jian-Guang Lou. 2022. Towards robustness of text-to-sql models against natural and realistic adversarial table perturbation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pa… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-squrve-unified-modular-framework-complex/