---
title: "Memo-SQL — paper by Zerui et al. (2026) — summary and ideas"
description: "Before inference, the authors build an error-correction memory from model mistakes on the BIRD training set. 42 references."
authors: ["Yang Zerui", "Weichuan Wang", "Yanwei Xu", "Linqi Song", "Yudai Matsuda", "Wei Han", "Bo Bai"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.253/"
doi: "10.18653/v1/2026.findings-acl.253"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zerui-2026-memo-sql-structured-decomposition-experience/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zerui-2026-memo-sql-structured-decomposition-experience/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/41/) / Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL

# Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL

**Authors:** Yang Zerui, [Weichuan Wang](https://md.research.elamur.ai/free/en/authors/weichuan-wang/), Yanwei Xu, [Linqi Song](https://md.research.elamur.ai/free/en/authors/linqi-song/), Yudai Matsuda, [Wei Han](https://md.research.elamur.ai/free/en/authors/wei-han/) and Bo Bai · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.253/) · [PDF](https://aclanthology.org/2026.findings-acl.253.pdf) · [DOI 10.18653/v1/2026.findings-acl.253](https://doi.org/10.18653/v1/2026.findings-acl.253) · [OpenAlex](https://openalex.org/W7166879450)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Memo-SQL targets two weaknesses of training-free NL2SQL systems built on test-time scaling (TTS). First, when an LLM decomposes questions freely, its runs tend to repeat the same reasoning, so ensembling adds little. Second, self-correction usually depends on fixed few-shot prompts and ignores past mistakes.

The framework handles decomposition with three explicit strategies: entity-wise, hierarchical and atomic sequential. Each sub-question is solved in a ReAct+Reflection loop that allows one corrective revision. The model then writes candidate queries in three syntactic styles: CTE, flat JOIN and nested subquery.

Before inference, the authors build an error-correction memory from model mistakes on the BIRD training set. Each erroneous query is labelled with error types and paired with fix suggestions. At inference, similar failure–fix cases are retrieved and placed in the prompt to guide refinement. A self-consistency score then picks the final query.

On BIRD, Memo-SQL reaches 68.5% execution accuracy, the best reported result among open methods that use no fine-tuning. It also needs roughly an order of magnitude less computation than heavy TTS systems such as Alpha-SQL. This makes accurate NL2SQL more practical for private, locally hosted deployments.

## Key points
- The memory stores entries of the form ⟨q, s⁺, s⁻, E, δ⟩: the question, the gold SQL, an incorrect SQL, error labels from a nine-type semantic taxonomy, and correction advice. Entries are embedded with GTE-base, using the question plus the SQL skeleton as the retrieval key.
- In the self-correction comparison on BIRD dev, Memo-SQL scores 68.5% EX. The uncorrected baseline gets 66.4%, direct correction 66.6%, DIN-SQL 66.5% and SOLID-SQL 67.4%. SHARE scores higher at 69.2%, but it requires fine-tuning three models.
- With Llama-3.1-8B, EX rises from 21.1% to 52.1%. Compared with Alpha-SQL, this setup uses about 14.8× fewer tokens and runs about 12.1× faster.
- In another reported comparison, Memo-SQL used 7,925 versus 150,344 tokens and took 145 s versus 1,839 s per query.
- The authors list three limitations. Errors in the memory are synthetic and may not match real user mistakes. Ambiguous questions can still derail decomposition. The multiple LLM calls are too slow for sub-second use cases.

*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

- [City University of Hong Kong](https://md.research.elamur.ai/free/en/universities/city-university-of-hong-kong/) — University, Hong Kong, China · 59 works · 3,480 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🌐 Computer Networks and Communications](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-networks-and-communications/) · 100 works

## Cite

Cite as: Yang Zerui, Weichuan Wang, Yanwei Xu, Linqi Song, Yudai Matsuda, Wei Han and Bo Bai. 2026. Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zerui2026memo,
  title = {{Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL}},
  author = {Yang Zerui, Weichuan Wang, Yanwei Xu, Linqi Song, Yudai Matsuda, Wei Han and Bo Bai},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.253},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.253}
}
```

- [← previous MemCoRL: Alternating Co-Optimization of Memory Retrieval and Utilization via Collaborative Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/liu-2026-memcorl-alternating-co-optimization-memory/)
- [next → MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents](https://md.research.elamur.ai/free/en/papers/van-2026-memorai-memory-organization-retrieval-adaptive/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/41/)

## References

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

1. Arian Askari, Christian Poelitz, and Xinye Tang. 2025. Magic: Generating self-correction guideline for in-context text-to-sql. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 23433–23441. [find](https://scholar.google.com/scholar?q=Arian+Askari%2C+Christian+Poelitz%2C+and+Xinye+Tang%2E+2025%2E+Magic%3A+Generating+self%2Dcorrection+guideline+for+in%2Dcontext+text%2Dto%2Dsql%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volume+)
2. 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](https://scholar.google.com/scholar?q=Zhenbiao+Cao%2C+Yuanlei+Zheng%2C+Zhihao+Fan%2C+Xiaojin+Zhang%2C+Wei+Chen%2C+and+Xiang+Bai%2E+2024%2E+Rsl%2Dsql%3A+Robust+schema+linking+in+text%2Dto%2Dsql+generation%2E+arXiv+preprint+arXiv%3A2411%2E00073%2E+%E2%80%94+%5BarXiv%3A2411%2E00073%5D%28h)
3. Mayur Datar, Nicole Immorlica, Piotr Indyk, and Vahab S. Mirrokni. 2004. Locality-sensitive hashing scheme based on p-stable distributions. In Proceedings of the Twentieth Annual Symposium on Computational Geometry, SCG ’04, page 253–262, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Mayur+Datar%2C+Nicole+Immorlica%2C+Piotr+Indyk%2C+and+Vahab+S%2E+Mirrokni%2E+2004%2E+Locality%2Dsensitive+hashing+scheme+based+on+p%2Dstable+distributions%2E+In+Proceedings+of+the+Twentieth+Annual+Symposium+on+Computat)
4. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. [BERT: pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). CoRR, abs/1810.04805.
5. Ju Fan, Zihui Gu, Songyue Zhang, Yuxin Zhang, Zui Chen, Lei Cao, Guoliang Li, Samuel Madden, Xiaoyong Du, and Nan Tang. 2024. Combining small language models and large language models for zero-shot nl2sql. Proceedings of the VLDB Endowment, 17(11):2750–2763. [find](https://scholar.google.com/scholar?q=Ju+Fan%2C+Zihui+Gu%2C+Songyue+Zhang%2C+Yuxin+Zhang%2C+Zui+Chen%2C+Lei+Cao%2C+Guoliang+Li%2C+Samuel+Madden%2C+Xiaoyong+Du%2C+and+Nan+Tang%2E+2024%2E+Combining+small+language+models+and+large+language+models+for+zero%2Dshot+nl)
6. Dawei Gao, Haibin Wang, Yaliang Li, Xiuyu Sun, Yichen Qian, Bolin Ding, and Jingren Zhou. 2023. [Text-to-sql empowered by large language models: A benchmark evaluation](https://md.research.elamur.ai/free/en/papers/gao-2023-text-sql-empowered-large-language/). arXiv preprint arXiv:2308.15363.
7. Xinyu Guan, Li Lyna Zhang, Yifei Liu, Ning Shang, Youran Sun, Yi Zhu, Fan Yang, and Mao Yang. 2025. [rstar-math: Small llms can master math reasoning with self-evolved deep thinking](https://md.research.elamur.ai/free/en/papers/guan-2025-rstar-math-small-llms-can/). arXiv preprint arXiv:2501.04519. 5138 9
8. Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou. 2023. [Large language models cannot self-correct reasoning yet](https://md.research.elamur.ai/free/en/papers/huang-2023-large-language-models-cannot-self/). arXiv preprint arXiv:2310.01798.
9. Weibin Liao, Xin Gao, Tianyu Jia, Rihong Qiu, Yifan Zhu, Yang Lin, Xu Chu, Junfeng Zhao, and Yasha Wang. 2025. Learnat: Learning nl2sql with ast-guided task decomposition for large language models. arXiv preprint arXiv:2504.02327. — [arXiv:2504.02327](https://arxiv.org/abs/2504.02327) [find](https://scholar.google.com/scholar?q=Weibin+Liao%2C+Xin+Gao%2C+Tianyu+Jia%2C+Rihong+Qiu%2C+Yifan+Zhu%2C+Yang+Lin%2C+Xu+Chu%2C+Junfeng+Zhao%2C+and+Yasha+Wang%2E+2025%2E+Learnat%3A+Learning+nl2sql+with+ast%2Dguided+task+decomposition+for+large+language+models%2E+ar)
10. Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang, Dayiheng Liu, Lei Zhang, Tianyu Liu, Jiajun Zhang, Bowen Yu, Keming Lu, and 1 others. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186. — [Qwen2.5-Coder Technical Report](https://md.research.elamur.ai/free/en/papers/hui-2024-qwen2-5-coder-technical-report/)
11. Geling Liu, Yunzhi Tan, Ruichao Zhong, Yuanzhen Xie, Lingchen Zhao, Qian Wang, Bo Hu, and Zang Li. 2025a. Solid-SQL: Enhanced schema-linking based in-context learning for robust text-to-SQL. In Proceedings of the 31st International Conference on Computational Linguistics, pages 9793–9803, Abu Dhabi,… [find](https://scholar.google.com/scholar?q=Geling+Liu%2C+Yunzhi+Tan%2C+Ruichao+Zhong%2C+Yuanzhen+Xie%2C+Lingchen+Zhao%2C+Qian+Wang%2C+Bo+Hu%2C+and+Zang+Li%2E+2025a%2E+Solid%2DSQL%3A+Enhanced+schema%2Dlinking+based+in%2Dcontext+learning+for+robust+text%2Dto%2DSQL%2E+In+Procee)
12. JDCHO. 2025. Joyagent-jdgenie. [find](https://scholar.google.com/scholar?q=JDCHO%2E+2025%2E+Joyagent%2Djdgenie%2E)
13. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
14. Yifu Liu, Yin Zhu, Yingqi Gao, Zhiling Luo, Xiaoxia Li, Xiaorong Shi, Yuntao Hong, Jinyang Gao, Yu Li, Bolin Ding, and 1 others. 2025b. Xiyan-sql: A novel multi-generator framework for text-to-sql. arXiv preprint arXiv:2507.04701. — [arXiv:2507.04701](https://arxiv.org/abs/2507.04701) [find](https://scholar.google.com/scholar?q=Yifu+Liu%2C+Yin+Zhu%2C+Yingqi+Gao%2C+Zhiling+Luo%2C+Xiaoxia+Li%2C+Xiaorong+Shi%2C+Yuntao+Hong%2C+Jinyang+Gao%2C+Yu+Li%2C+Bolin+Ding%2C+and+1+others%2E+2025b%2E+Xiyan%2Dsql%3A+A+novel+multi%2Dgenerator+framework+for+text%2Dto%2Dsql%2E+ar)
15. Dongjun Lee, Choongwon Park, Jaehyuk Kim, and Heesoo Park. 2024. [Mcs-sql: Leveraging multiple prompts and multiple-choice selection for text-to-sql generation](https://md.research.elamur.ai/free/en/papers/lee-2025-mcs-sql-leveraging-multiple-prompts/). arXiv preprint arXiv:2405.07467.
16. Karime Maamari, Fadhil Abubaker, Daniel Jaroslawicz, and Amine Mhedhbi. 2024. The death of schema linking? text-to-sql in the age of well-reasoned language models. arXiv preprint arXiv:2408.07702. — [arXiv:2408.07702](https://arxiv.org/abs/2408.07702) [find](https://scholar.google.com/scholar?q=Karime+Maamari%2C+Fadhil+Abubaker%2C+Daniel+Jaroslawicz%2C+and+Amine+Mhedhbi%2E+2024%2E+The+death+of+schema+linking%3F+text%2Dto%2Dsql+in+the+age+of+well%2Dreasoned+language+models%2E+arXiv+preprint+arXiv%3A2408%2E07702%2E+%E2%80%94+%5B)
17. Boyan Li, Chong Chen, Zhujun Xue, Yinan Mei, and Yuyu Luo. 2025a. Deepeye-sql: A software-engineering-inspired text-to-sql framework. arXiv preprint arXiv:2510.17586. — [arXiv:2510.17586](https://arxiv.org/abs/2510.17586) [find](https://scholar.google.com/scholar?q=Boyan+Li%2C+Chong+Chen%2C+Zhujun+Xue%2C+Yinan+Mei%2C+and+Yuyu+Luo%2E+2025a%2E+Deepeye%2Dsql%3A+A+software%2Dengineering%2Dinspired+text%2Dto%2Dsql+framework%2E+arXiv+preprint+arXiv%3A2510%2E17586%2E+%E2%80%94+%5BarXiv%3A2510%2E17586%5D%28https%3A%2F%2Farxi)
18. Solomon Negash and Paul Gray. 2008. Business intelligence. In Handbook on Decision Support Systems 2: Variations, pages 175–193. Springer. [find](https://scholar.google.com/scholar?q=Solomon+Negash+and+Paul+Gray%2E+2008%2E+Business+intelligence%2E+In+Handbook+on+Decision+Support+Systems+2%3A+Variations%2C+pages+175%E2%80%93193%2E+Springer%2E)
19. Boyan Li, Yuyu Luo, Chengliang Chai, Guoliang Li, and Nan Tang. 2024a. The dawn of natural language to sql: Are we fully ready? arXiv preprint arXiv:2406.01265. — [arXiv:2406.01265](https://arxiv.org/abs/2406.01265) [find](https://scholar.google.com/scholar?q=Boyan+Li%2C+Yuyu+Luo%2C+Chengliang+Chai%2C+Guoliang+Li%2C+and+Nan+Tang%2E+2024a%2E+The+dawn+of+natural+language+to+sql%3A+Are+we+fully+ready%3F+arXiv+preprint+arXiv%3A2406%2E01265%2E+%E2%80%94+%5BarXiv%3A2406%2E01265%5D%28https%3A%2F%2Farxiv%2Eorg%2F)
20. Boyan Li, Jiayi Zhang, Ju Fan, Yanwei Xu, Chong Chen, Nan Tang, and Yuyu Luo. 2025b. Alpha-sql: Zero-shot text-to-sql using monte carlo tree search. arXiv preprint arXiv:2502.17248. — [arXiv:2502.17248](https://arxiv.org/abs/2502.17248) [find](https://scholar.google.com/scholar?q=Boyan+Li%2C+Jiayi+Zhang%2C+Ju+Fan%2C+Yanwei+Xu%2C+Chong+Chen%2C+Nan+Tang%2C+and+Yuyu+Luo%2E+2025b%2E+Alpha%2Dsql%3A+Zero%2Dshot+text%2Dto%2Dsql+using+monte+carlo+tree+search%2E+arXiv+preprint+arXiv%3A2502%2E17248%2E+%E2%80%94+%5BarXiv%3A2502%2E1724)
21. Haoyang Li, Jing Zhang, Hanbing Liu, Ju Fan, Xiaokang Zhang, Jun Zhu, Renjie Wei, Hongyan Pan, Cuiping Li, and Hong Chen. 2024b. [Codes: Towards building open-source language models for text-to-sql](https://md.research.elamur.ai/free/en/papers/li-2024-codes-towards-building-open-source/). Proceedings of the ACM on Management of Data, 2(3):1–28.
22. Jinyang Li, Binyuan Hui, Ge Qu, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Ruiying Geng, Nan Huo, and 1 others. 2023a. [Can llm already serve as a database interface? a big bench for large-scale database grounded text-to-sqls](https://md.research.elamur.ai/free/en/papers/li-2023-llm-already-serve-database-interface/). Advances in Neural Information Processing Systems, 36:42330–…
23. Xiuwen Li, Qifeng Cai, Yang Shu, Chenjuan Guo, and Bin Yang. 2025c. Aid-sql: Adaptive in-context learning of text-to-sql with difficulty-aware instruction and retrieval-augmented generation. In 2025 IEEE 41st International Conference on Data Engineering (ICDE), pages 3945–3957. IEEE. [find](https://scholar.google.com/scholar?q=Xiuwen+Li%2C+Qifeng+Cai%2C+Yang+Shu%2C+Chenjuan+Guo%2C+and+Bin+Yang%2E+2025c%2E+Aid%2Dsql%3A+Adaptive+in%2Dcontext+learning+of+text%2Dto%2Dsql+with+difficulty%2Daware+instruction+and+retrieval%2Daugmented+generation%2E+In+2025+I)
24. Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023b. [Towards general text embeddings with multi-stage contrastive learning](https://md.research.elamur.ai/free/en/papers/li-2023-towards-general-text-embeddings-multi/). arXiv preprint arXiv:2308.03281.
25. Mohammadreza Pourreza, Hailong Li, Ruoxi Sun, Yeounoh Chung, Shayan Talaei, Gaurav Tarlok Kakkar, Yu Gan, Amin Saberi, Fatma Ozcan, and Sercan O Arik. 2024. Chase-sql: Multi-path reasoning and preference optimized candidate selection in text-to-sql. arXiv preprint arXiv:2410.01943. — [arXiv:2410.01943](https://arxiv.org/abs/2410.01943) [find](https://scholar.google.com/scholar?q=Mohammadreza+Pourreza%2C+Hailong+Li%2C+Ruoxi+Sun%2C+Yeounoh+Chung%2C+Shayan+Talaei%2C+Gaurav+Tarlok+Kakkar%2C+Yu+Gan%2C+Amin+Saberi%2C+Fatma+Ozcan%2C+and+Sercan+O+Arik%2E+2024%2E+Chase%2Dsql%3A+Multi%2Dpath+reasoning+and+prefere)
26. Mohammadreza Pourreza and Davood Rafiei. 2023. [Din-sql: Decomposed in-context learning of text-to-sql with self-correction](https://md.research.elamur.ai/free/en/papers/pourreza-2023-din-sql-decomposed-context-learning/). In Advances in Neural Information Processing Systems, volume 36, pages 36339–36348. Curran Associates, Inc.
27. Mohammadreza Pourreza and Davood Rafiei. 2024. Dts-sql: Decomposed text-to-sql with small large language models. arXiv preprint arXiv:2402.01117. [find](https://scholar.google.com/scholar?q=Mohammadreza+Pourreza+and+Davood+Rafiei%2E+2024%2E+Dts%2Dsql%3A+Decomposed+text%2Dto%2Dsql+with+small+large+language+models%2E+arXiv+preprint+arXiv%3A2402%2E01117%2E)
28. Mohammadreza Pourreza, Shayan Talaei, Ruoxi Sun, Xingchen Wan, Hailong Li, Azalia Mirhoseini, Amin Saberi, Sercan Arik, and 1 others. 2025. Reasoning-sql: Reinforcement learning with sql tailored partial rewards for reasoning-enhanced text-to-sql. arXiv preprint arXiv:2503.23157. — [arXiv:2503.23157](https://arxiv.org/abs/2503.23157) [find](https://scholar.google.com/scholar?q=Mohammadreza+Pourreza%2C+Shayan+Talaei%2C+Ruoxi+Sun%2C+Xingchen+Wan%2C+Hailong+Li%2C+Azalia+Mirhoseini%2C+Amin+Saberi%2C+Sercan+Arik%2C+and+1+others%2E+2025%2E+Reasoning%2Dsql%3A+Reinforcement+learning+with+sql+tailored+part)
29. Yang Qin, Chao Chen, Zhihang Fu, Ze Chen, Dezhong Peng, Peng Hu, and Jieping Ye. 2024. Route: Robust multitask tuning and collaboration for text-to-sql. arXiv preprint arXiv:2412.10138. — [arXiv:2412.10138](https://arxiv.org/abs/2412.10138) [find](https://scholar.google.com/scholar?q=Yang+Qin%2C+Chao+Chen%2C+Zhihang+Fu%2C+Ze+Chen%2C+Dezhong+Peng%2C+Peng+Hu%2C+and+Jieping+Ye%2E+2024%2E+Route%3A+Robust+multitask+tuning+and+collaboration+for+text%2Dto%2Dsql%2E+arXiv+preprint+arXiv%3A2412%2E10138%2E+%E2%80%94+%5BarXiv%3A2412%2E)
30. Ge Qu, Jinyang Li, Bowen Qin, Xiaolong Li, Nan Huo, Chenhao Ma, and Reynold Cheng. 2025. Share: An slm-based hierarchical action correction assistant for text-to-sql. arXiv preprint arXiv:2506.00391. 5139 10 [find](https://scholar.google.com/scholar?q=Ge+Qu%2C+Jinyang+Li%2C+Bowen+Qin%2C+Xiaolong+Li%2C+Nan+Huo%2C+Chenhao+Ma%2C+and+Reynold+Cheng%2E+2025%2E+Share%3A+An+slm%2Dbased+hierarchical+action+correction+assistant+for+text%2Dto%2Dsql%2E+arXiv+preprint+arXiv%3A2506%2E00391%2E+)
31. Jie Shi, Bo Xu, Jiaqing Liang, Yanghua Xiao, Jia Chen, Chenhao Xie, Peng Wang, and Wei Wang. 2025. Gen-sql: Efficient text-to-sql by bridging natural language question and database schema with pseudo-schema. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3794… [find](https://scholar.google.com/scholar?q=Jie+Shi%2C+Bo+Xu%2C+Jiaqing+Liang%2C+Yanghua+Xiao%2C+Jia+Chen%2C+Chenhao+Xie%2C+Peng+Wang%2C+and+Wei+Wang%2E+2025%2E+Gen%2Dsql%3A+Efficient+text%2Dto%2Dsql+by+bridging+natural+language+question+and+database+schema+with+pseudo%2D)
32. 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](https://scholar.google.com/scholar?q=Shayan+Talaei%2C+Mohammadreza+Pourreza%2C+Yu%2DChen+Chang%2C+Azalia+Mirhoseini%2C+and+Amin+Saberi%2E+2024%2E+Chess%3A+Contextual+harnessing+for+efficient+sql+synthesis%2E+arXiv+preprint+arXiv%3A2405%2E16755%2E+%E2%80%94+%5BarXiv%3A2405%2E)
33. Llama Team. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). Preprint, arXiv:2407.21783.
34. Qwen Team. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388.
35. Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, Linzheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, and 1 others. 2023. [Mac-sql: A multi-agent collaborative framework for text-to-sql](https://md.research.elamur.ai/free/en/papers/wang-2025-mac-sql-multi-agent-collaborative/). arXiv preprint arXiv:2312.11242.
36. 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](https://scholar.google.com/scholar?q=Xiangjin+Xie%2C+Guangwei+Xu%2C+Lingyan+Zhao%2C+and+Ruijie+Guo%2E+2025%2E+Opensearch%2Dsql%3A+Enhancing+text%2Dto%2Dsql+with+dynamic+few%2Dshot+and+consistency+alignment%2E+Proceedings+of+the+ACM+on+Management+of+Data%2C+3%283%29)
37. Yuanzhen Xie, Xinzhou Jin, Tao Xie, Matrixmxlin Matrixmxlin, Liang Chen, Chenyun Yu, Cheng Lei, ChengXiang Zhuo, Bo Hu, and Zang Li. 2024. Decomposition for enhancing attention: Improving llm-based text-to-sql through workflow paradigm. In Findings of the Association for Computational Linguistics: A… [find](https://scholar.google.com/scholar?q=Yuanzhen+Xie%2C+Xinzhou+Jin%2C+Tao+Xie%2C+Matrixmxlin+Matrixmxlin%2C+Liang+Chen%2C+Chenyun+Yu%2C+Cheng+Lei%2C+ChengXiang+Zhuo%2C+Bo+Hu%2C+and+Zang+Li%2E+2024%2E+Decomposition+for+enhancing+attention%3A+Improving+llm%2Dbased+te)
38. Zerui Yang, Yuwei Wan, Siyu Yan, Yudai Matsuda, Tong Xie, Bram Hoex, and Linqi Song. 2025. Drugmcts: a drug repurposing framework combining multi-agent, rag and monte carlo tree search. arXiv preprint arXiv:2507.07426. — [arXiv:2507.07426](https://arxiv.org/abs/2507.07426) [find](https://scholar.google.com/scholar?q=Zerui+Yang%2C+Yuwei+Wan%2C+Siyu+Yan%2C+Yudai+Matsuda%2C+Tong+Xie%2C+Bram+Hoex%2C+and+Linqi+Song%2E+2025%2E+Drugmcts%3A+a+drug+repurposing+framework+combining+multi%2Dagent%2C+rag+and+monte+carlo+tree+search%2E+arXiv+preprint)
39. 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](https://md.research.elamur.ai/free/en/papers/yu-2018-spider-large-scale-human-labeled/). arXiv preprint arXiv:1809.08887.
40. Shuozhi Yuan, Liming Chen, Miaomiao Yuan, Jin Zhao, Haoran Peng, and Wenming Guo. 2025. Mcts-sql: An effective framework for text-to-sql with monte carlo tree search. arXiv preprint arXiv:2501.16607. — [arXiv:2501.16607](https://arxiv.org/abs/2501.16607) [find](https://scholar.google.com/scholar?q=Shuozhi+Yuan%2C+Liming+Chen%2C+Miaomiao+Yuan%2C+Jin+Zhao%2C+Haoran+Peng%2C+and+Wenming+Guo%2E+2025%2E+Mcts%2Dsql%3A+An+effective+framework+for+text%2Dto%2Dsql+with+monte+carlo+tree+search%2E+arXiv+preprint+arXiv%3A2501%2E16607%2E+)
41. Fuheng Zhao, Shaleen Deep, Fotis Psallidas, Avrilia Floratou, Divyakant Agrawal, and Amr El Abbadi. 2024. Sphinteract: Resolving ambiguities in nl2sql through user interaction. Proceedings of the VLDB Endowment, 18(4):1145–1158. [find](https://scholar.google.com/scholar?q=Fuheng+Zhao%2C+Shaleen+Deep%2C+Fotis+Psallidas%2C+Avrilia+Floratou%2C+Divyakant+Agrawal%2C+and+Amr+El+Abbadi%2E+2024%2E+Sphinteract%3A+Resolving+ambiguities+in+nl2sql+through+user+interaction%2E+Proceedings+of+the+VLDB)
42. Qihao Zhu, Daya Guo, Zhihong Shao, Dejian Yang, Peiyi Wang, Runxin Xu, Y Wu, Yukun Li, Huazuo Gao, Shirong Ma, and 1 others. 2024. [Deepseek-coder-v2: Breaking the barrier of closed-source 5140 11 models in code intelligence](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2024-deepseek-coder-v2-breaking-barrier/). arXiv:2406.11931. arXiv preprint

*Updated 2 November 2026*