DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework
Boyan Li, Chong Chen, Zhujun Xue, Yinan Mei, Yuyu Luo
Abstract
Large language models (LLMs) have advanced Text-to-SQL, yet existing solutions still fall short of system-level reliability. The limitation is not merely in individual modules -- e.g. , schema linking, reasoning, and verification -- but more critically in the lack of structured orchestration that enforces correctness across the entire workflow. This gap motivates a paradigm shift: treating Text-to-SQL not as free-form language generation but as a software-engineering problem that demands structured, verifiable orchestration. We present D eep E ye -SQL, a software-engineering-inspired framework that reframes Text-to-SQL as the development of a small software program, executed through a verifiable process guided by the Software Development Life Cycle (SDLC). D eep E ye integrates four synergistic stages: it grounds user intent through robust schema linking, enforcing relational closure; enhances fault tolerance with N-version SQL generation; ensures deterministic verification via a ''Syntax-Logic-Quality'' tool-chain that intercepts errors pre-execution; and introduces confidence-aware selection that leverages execution-guided adjudication to resolve ambiguity beyond simple majority voting. Leveraging open-source MoE LLMs ( 30B total, 3B activated parameters) without any fine-tuning, D eep E ye achieves 73.5% execution accuracy on BIRD-Dev, 75.07% on the official BIRD-Test leaderboard, and 89.8% on Spider-Test, outperforming state-of-the-art solutions that rely on larger models or extensive training. This highlights that principled orchestration, rather than LLM scaling alone, is key to achieving system-level reliability in Text-to-SQL.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
11 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations cites Natural Language to Visualization by Neural Machine Translation
- VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations cites Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs
- OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
- OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision cites DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
- OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision cites Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
- OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision cites Efficient Memory Management for Large Language Model Serving with PagedAttention
- Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation cites DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
Cited by top-tier papers11
- VisJudge-Bench: Aesthetics and Quality Assessment of VisualizationsYupeng Xie, Zhiyang Zhang, Yifan Wu, Sirong Lu et al.ICLR 2026 · 23 citations
- AOrchestra: Automating Sub-Agent Creation for Agentic OrchestrationJianhao Ruan, Zhihao Xu, Yiran Peng, Fashen Ren et al.ICML 2026 · 19 citations
- InteractComp: Evaluating Search Agents With Ambiguous QueriesMingyi Deng, Lijun Huang, Yani Fan, Fanqi Kong et al.ICML 2026 · 11 citations
- Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMsZhuowen Liang, Xiaotian Lin, Zhengxuan Zhang, Yuyu Luo et al.ICLR 2026 · 6 citations
- OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate SupervisionRuilin Hu, Yuyu Luo, Guoliang Li, Shuangqiao Wu et al.VLDB 2026 · 4 citations
Builds on22
- Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
- DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-CorrectionMohammadreza Pourreza, Davood RafieiNeurIPS 2023 · 909 citations
- Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le et al.ICLR 2023 · 681 citations
- Text-to-SQL Empowered by Large Language Models: A Benchmark EvaluationDawei Gao, Haibin Wang, Yaliang Li, Xiuyu Sun et al.VLDB 2024 · 609 citations
- Natural Language to Visualization by Neural Machine TranslationYuyu Luo, Nan Tang, Guoliang Li, Jiawei Tang et al.IEEE VIS 2021 · 145 citations
Related papers
- APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQLBowen Cao, Weibin Liao, Yushi Sun, Dong Fang et al.KDD 2026 · 7 citations
- Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow ParadigmYuanzhen Xie, Xinzhou Jin, Tao Xie, Mingxiong Lin et al.ACL Findings 2024 · 34 citations
- SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMsYu Guo, Dong Jin, Shenghao Ye, Shuangwu Chen et al.ACL Findings 2025 · 3 citations
- MARS-SQL: A Multi-Agent Reinforcement Learning Framework For Text-To-SQLHaolin Yang, Jipeng Zhang, Zhitao He, Alexander Zhou et al.ICML 2026 · 12 citations
- SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQLGeonho Lee, Min-Soo KimVLDB 2026
