Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards
Summary: Reward-SQL introduces CoCTE, progressively composing SQL with execution-validated intermediate views and structured CTEs. Its entropy-weighted, execution-aware process reward model supervises both RL training and inference, improving accuracy, interpretability, and cross-domain generalization. (summarized by gpt-5.6-luna on Jul 26 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yuxin Zhang (Renmin University of China)
- 2. Meihao Fan (Renmin University of China)
- 3. Ju Fan (Renmin University of China)
- 4. Mingyang Yi (Renmin University of China)
- 5. Yuyu Luo (Hong Kong University of Science and Technology)
- 6. Guoliang Li (Tsinghua University)
- 7. Bin Wu (Alibaba)
- 8. Wenchao Zhou (Alibaba)
BibTeX Citation
@inproceedings{zhang_sigmod26,
title = {{Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards}},
author = {Zhang, Yuxin and Fan, Meihao and Fan, Ju and Yi, Mingyang and Luo, Yuyu and Li, Guoliang and Wu, Bin and Zhou, Wenchao},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802105},
url = {https://dl.acm.org/doi/10.1145/3802105},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 5 of 5 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,870 | Natural Language to SQL: State of the Art and Open Problems | 2025 | VLDB | 5.2043672e-05 |
| 10,217 | DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework | 2026 | SIGMOD | 5.093636e-05 |
| 10,304 | VecBench: A Controllable Benchmark for Filtered Vector Search: [Experiments & Analysis] | 2026 | SIGMOD | 5.093636e-05 |
| 10,537 | TACO: A Benchmark for Open-Domain Text-to-SQL with Ambiguous and Cross-Database Queries | 2026 | VLDB | 5.093636e-05 |
| 10,931 | AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework | 2025 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB | 0.00022468369 |
| 756 | CodeS: Towards Building Open-source Language Models for Text-to-SQL | 2024 | SIGMOD | 0.0001431656 |
| 2,039 | ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems | 2024 | VLDB | 9.2721259e-05 |
| 2,395 | OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale | 2025 | VLDB | 8.6355093e-05 |
| 2,748 | Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning | 2023 | SIGMOD | 8.1707811e-05 |
| 3,787 | Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL | 2024 | VLDB | 7.1249098e-05 |
| 9,870 | Natural Language to SQL: State of the Art and Open Problems | 2025 | VLDB | 5.2043672e-05 |
| 10,931 | AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework | 2025 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,732 | RTS+: Reliable Text to SQL | 2025 | SIGMOD |
| 2 | 7,809 | Can Large Language Models Be Query Optimizer for Relational Databases? | 2026 | SIGMOD |
| 3 | 6,259 | R-Bot: An LLM-based Query Rewrite System | 2025 | VLDB |
| 4 | 10,556 | OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision | 2026 | VLDB |
| 5 | 2,748 | Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning | 2023 | SIGMOD |
| 6 | 6,936 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 7 | 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 8 | 2,553 | LLM-R^2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency | 2025 | VLDB |
| 9 | 10,398 | Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding | 2026 | SIGMOD |
| 10 | 5,169 | LearnedSQLGen: Constraint-aware SQL Generation using Reinforcement Learning | 2022 | SIGMOD |