SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning

arXiv:2608.00485 · cs.CL · Submitted 2026-08-01 · Read on arXiv

cs.CL

Submitted: 2026-08-01

Updated: 2026-10-08

Comments: 9 pages,6 figures, Underreview

Code: https://github.com/Ffunkytao/SERL-SQL

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Text-to-SQL — 37× in this paper · explained in 4 episodes
• Distillation — 19× in this paper · explained in 2 episodes
• GRPO — 17× in this paper · explained in 6 episodes
• Reinforcement Learning — 15× in this paper · explained in 4 episodes
• Accuracy — 13× in this paper · explained in 1 episode
• Credit assignment — 11× in this paper · explained in 3 episodes
• Grounding — 11× in this paper · explained in 3 episodes
• Policy distillation — 11× in this paper · explained in 2 episodes
• On-Policy Distillation — 10× in this paper · explained in 3 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• Consistency — 5× in this paper · explained in 3 episodes
• Student Policy — 5× in this paper · explained in 2 episodes
• Papers — 3× in this paper · explained in 3 episodes
• Self-Distillation — 3× in this paper · explained in 7 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• GRPO Objective — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 14 episodes
• Iterative Refinement — 2× in this paper · explained in 5 episodes
• Test-Time Scaling — 2× in this paper · explained in 4 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generator — 1× in this paper · explained in 2 episodes
• Hyperparameters — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 7 episodes
• Information Leakage — 1× in this paper · explained in 2 episodes
• Multi-agent Collaborative Framework — 1× in this paper · explained in 2 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 5 episodes

Sources

• Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL
• Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
• Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization
• A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL
• PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning
• Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL
• Qwen2.5-Coder Technical Report
• TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
• DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework
• On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
• Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
• What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
• A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?
• Self-Distilled Agentic Reinforcement Learning
• SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning
• CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL
• DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• CHESS: Contextual Harnessing for Efficient SQL Synthesis

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering