# SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestration

arXiv: https://arxiv.org/abs/2606.23537 · HTML: https://mlsanity.com/paper/2606.23537/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 59 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 30 of 39)

- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [CodeS: Towards Building Open-source Language Models for Text-to-SQL](https://mlsanity.com/paper/2402.16347/) (2024)
- [C3: Zero-shot Text-to-SQL with ChatGPT](https://mlsanity.com/paper/2307.07306/) (2023)
- [MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL](https://mlsanity.com/paper/2312.11242/) (2023)
- [The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks](https://mlsanity.com/paper/2502.08235/) (2025)
- [Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL](https://mlsanity.com/paper/2406.08426/) (2024)
- [The Dawn of Natural Language to SQL: Are We Fully Ready?](https://mlsanity.com/paper/2406.01265/) (2024)
- [Exploring Chain-of-Thought Style Prompting for Text-to-SQL](https://mlsanity.com/paper/2305.14215/) (2023)
- [FlowReasoner: Reinforcing Query-Level Meta-Agents](https://mlsanity.com/paper/2504.15257/) (2025)
- [Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL](https://mlsanity.com/paper/2503.23157/) (2025)
- [OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment](https://mlsanity.com/paper/2502.14913/) (2025)
- [RSL-SQL: Robust Schema Linking in Text-to-SQL Generation](https://mlsanity.com/paper/2411.00073/) (2024)
- [ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems](https://mlsanity.com/paper/2306.04743/) (2023)
- [XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL](https://mlsanity.com/paper/2507.04701/) (2025)
- [Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL](https://mlsanity.com/paper/2505.20315/) (2025)
- [AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration](https://mlsanity.com/paper/2602.03786/) (2026)
- [NL2SQL-BUGs: A Benchmark for Detecting Semantic Errors in NL2SQL Translation](https://mlsanity.com/paper/2503.11984/) (2025)
- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework](https://mlsanity.com/paper/2510.17586/) (2025)
- [Are Large Language Models Good Statisticians?](https://mlsanity.com/paper/2406.07815/) (2024)
- [Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards](https://mlsanity.com/paper/2505.04671/) (2025)
- [Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling](https://mlsanity.com/paper/2509.24403/) (2025)
- [Learning to Orchestrate Agents in Natural Language with the Conductor](https://mlsanity.com/paper/2512.04388/) (2025)
- [SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL](https://mlsanity.com/paper/2502.11741/) (2025)
- [nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning](https://mlsanity.com/paper/2503.12880/) (2025)

## Built on by (most cited first, 1 of 1)

- [DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces](https://mlsanity.com/paper/2608.03451/) (2026)

## Abstract (arXiv)

Text-to-SQL enables users to access relational databases via natural language, but real-world settings remain challenging due to coordinated reasoning over complex database environments. Existing systems often use multi-stage pipelines or reasoning models specialized for individual stages. However, fixed pipelines rely on predefined stage orders, limiting their adaptivity to query demands and intermediate evidence. Recent orchestration-based methods provide flexibility by composing specialized modules for each query, but typical plan-then-execute approaches still commit to a complete workflow before execution and cannot adapt to intermediate artifacts and feedback. In this paper, we propose SQLConductor, a step-wise orchestration learning framework for Text-to-SQL. SQLConductor formulates Text-to-SQL subtasks as specialized actions for workflow composition and trains a policy model to select the next action based on intermediate artifacts and feedback. To learn this policy, SQLConductor introduces Search-to-Policy Learning, which uses Monte Carlo Tree Search to explore candidate workflows and stability estimation to identify robust supervision. The policy model is trained with Stability-weighted Supervised Fine-tuning to prioritize high-quality orchestration patterns and further enhanced through Curriculum Reinforcement Learning. This transforms offline workflow search into a deployable policy for step-wise orchestration at inference time. Experiments on BIRD-Dev and out-of-distribution datasets show that SQLConductor achieves superior execution accuracy and strong generalization, reaching 73.2% EX on BIRD-Dev with a compact orchestration policy coordinating frozen larger action models, outperforming prior methods that directly train comparable or larger Text-to-SQL backbones. Further analyses show that the learned policy adapts orchestration to diverse query demands.