# DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework

arXiv: https://arxiv.org/abs/2510.17586 · HTML: https://mlsanity.com/paper/2510.17586/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2025.

## Built on by (most cited first, 28 of 28)

- [AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration](https://mlsanity.com/paper/2602.03786/) (2026)
- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [InteractComp: Evaluating Search Agents With Ambiguous Queries](https://mlsanity.com/paper/2510.24668/) (2025)
- [InfoPO: Information-Driven Policy Optimization for User-Centric Agents](https://mlsanity.com/paper/2603.00656/) (2026)
- [Harnessing Agentic Evolution](https://mlsanity.com/paper/2605.13821/) (2026)
- [Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL](https://mlsanity.com/paper/2601.10011/) (2026)
- [FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents](https://mlsanity.com/paper/2605.02815/) (2026)
- [Text2GraphQuery-Bench: A Text to Graph Query Benchmark](https://mlsanity.com/paper/2602.11745/) (2026)
- [DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces](https://mlsanity.com/paper/2608.03451/) (2026)
- [ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement](https://mlsanity.com/paper/2603.03742/) (2026)
- [Unsupervised Skill Discovery for Agentic Data Analysis](https://mlsanity.com/paper/2606.06416/) (2026)
- [SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestration](https://mlsanity.com/paper/2606.23537/) (2026)
- [IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Models](https://mlsanity.com/paper/2602.05385/) (2026)
- [Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System](https://mlsanity.com/paper/2603.07449/) (2026)
- [ROSE: An Intent-Centered Evaluation Metric for NL2SQL](https://mlsanity.com/paper/2604.12988/) (2026)
- [SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback](https://mlsanity.com/paper/2606.01246/) (2026)
- [CAPER: Clause-Aligned Process Supervision for Text-to-SQL](https://mlsanity.com/paper/2606.03327/) (2026)
- [SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing](https://mlsanity.com/paper/2606.11424/) (2026)
- [DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL](https://mlsanity.com/paper/2606.17821/) (2026)
- [SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning](https://mlsanity.com/paper/2608.00485/) (2026)
- [From Test-Time Scaling to Reusable Memory: Measuring Crystallization in Text-to-SQL](https://mlsanity.com/paper/2608.07213/) (2026)
- [DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation](https://mlsanity.com/paper/2608.11889/) (2026)
- [Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQL](https://mlsanity.com/paper/2608.28432/) (2026)
- [Data Agents: Agentic Data Systems](https://mlsanity.com/paper/2609.24137/) (2026)
- [ModularSQL: A Runtime Guardrail for the Multiplicity Blind Spot in Text-to-SQL](https://mlsanity.com/paper/2609.29573/) (2026)
- [TQTS-Bench: A Multi-Syntax Benchmark for Text-to-Query over Time-Series Databases](https://mlsanity.com/paper/2609.34783/) (2026)
- [ARCS: Towards Precise Text-to-SQL via Structured Disambiguation](https://mlsanity.com/paper/2610.09396/) (2026)
- [VeriPIE: Checkable Query Plans and Evidence-Guided Selection for Text-to-SQL](https://mlsanity.com/paper/2610.17493/) (2026)

## Abstract (arXiv)

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 DeepEye-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). DeepEye-SQL 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, DeepEye-SQL 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.