mlsanityData to 7 Oct 2026

AGRO-SQL: Agentic Group-Relative Optimization with High-Fidelity Data Synthesis

arXiv 2512.23366 ↗First posted 29 Dec 2025cs.DB cs.AIcited by 2

On the map: LLM reasoning → Reinforcement learning for reasoning

also in 1 more
Abstract (arXiv)

The advancement of Text-to-SQL systems is currently hindered by the scarcity of high-quality training data and the limited reasoning capabilities of models in complex scenarios. In this paper, we propose a holistic framework that addresses these issues through a dual-centric approach. From a Data-Centric perspective, we construct an iterative data factory that synthesizes RL-ready data characterized by high correctness and precise semantic-logic alignment, ensured by strict verification. From a Model-Centric perspective, we introduce a novel Agentic Reinforcement Learning framework. This framework employs a Diversity-Aware Cold Start stage to initialize a robust policy, followed by Group Relative Policy Optimization (GRPO) to refine the agent's reasoning via environmental feedback. Extensive experiments on BIRD and Spider benchmarks demonstrate that our synergistic approach achieves state-of-the-art performance among single-model methods.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 21 of its 29 references that are in the map. First posted on arXiv 29 Dec 2025.

Builds on

21 of 29 references.

References · 21

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  3. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  4. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  5. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  6. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  7. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  8. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 90
  9. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
  10. 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 51
  11. 2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
  12. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLcited by 38
9 more
  1. 2022Importance of Synthesizing High-quality Data for Text-to-SQL Parsingcited by 27
  2. 2025LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQLcited by 26
  3. 2025Automatic Metadata Extraction for Text-to-SQLcited by 25
  4. 2024SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Mergingcited by 16
  5. 2025MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQLcited by 14
  6. 2025MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQLcited by 10
  7. 2025ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQLcited by 8
  8. 2025Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Rewardcited by 7
  9. 2025SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026SPPO: Sequence-Level PPO for Long-Horizon Reasoning Taskscited by 7
  2. 2026TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemascited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning
  2. 2026ReToolSQL: Agentic Reinforcement Learning for Robust Text-to-SQL
  3. 2025Training-Free Group Relative Policy Optimization
  4. 2026SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL
  5. 2025DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
  6. 2025Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning
  7. 2025Tree Search for LLM Agent Reinforcement Learning
  8. 2026SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning