SERL‑SQL introduces a selective execution‑grounded reinforcement learning framework for multi‑turn Text‑to‑SQL agents. It samples on‑policy interaction trajectories and employs a training‑only teacher to re‑score student actions using execution feedback, converting the teacher‑student likelihood gap into bounded, masked weights that reweight GRPO advantages only on SQL and tool‑action tokens. Experiments on BIRD, Spider, and cross‑domain benchmarks show competitive performance, achieving 76.56% execution accuracy on BIRD‑Dev and 89.92% on Spider‑Test, and the reward‑based selection strategy approaches the oracle Best‑of‑N upper bound.
By Tao Liu, Tao Feng, Xiangheng Li, Jinwang Song, Yifan Li, Xiaoqing Cheng, Dixuan Zhang, Siquan Li, Lin Lan, Hongying Zan, Kunli Zhang, Chao Wu
arXiv:2603.20004v4 Announce Type: replace-cross
Abstract: Translating natural language questions to SQL queries (Text-to-SQL) is a long-standing problem in database research. Recent efforts have focu...
By Yuxuan Zhu, Tengjun Jin, Yoojin Choi, Daniel Kang
arXiv:2607. 20489v1 Announce Type: new Abstract: Text-to-SQL has advanced rapidly with large language models, but complex database queries still require reasoning beyond one-shot generation, including multi-step decomposition, execution-based diagnosis, and targeted correction.
By Jiawei Zhou, Jianwei Wang, Chenyu Zhou, Chaojian Shi, Ming Dong, Kai Wang
arXiv:2606. 01246v1 Announce Type: new Abstract: Text-to-SQL on complex schemas is unreliable on a single pass, so recent systems generate multiple SQL candidates and let voting filter out errors.
By Leo Luo, Haining Xie, Siqi Shen, Zhipeng Ma, Rui Ling, Hang Xu, Hefeng Jiang, Dingwei Chen, Yang Li, Peng Chen, Jie Jiang
J-Zero introduces a unified Challenger–Solver–Judge self‑evolution framework that operates without any initial data. The Challenger and Solver co‑evolve through adversarial task generation and response improvement, while the Judge adapts using known preference pairs derived from the Solver’s outputs rather than its own scores. Experiments show J‑Zero surpasses baselines by 4.2 points on verifiable tasks and 8.0 points on unverifiable tasks, maintaining improvement over ten iterations versus baseline degradation after two.
By Gyouk Chu, Myeongho Jeon, Teresa Yeo, Eunho Yang
arXiv:2601. 07055v2 Announce Type: replace Abstract: As high-quality data becomes increasingly difficult to obtain, self-evolution without curated training data has emerged as a promising paradigm.
By Zhenrui Yue, Kartikeya Upasani, Xianjun Yang, Suyu Ge, Shaoliang Nie, Yuning Mao, Zhe Liu, Dong Wang
HarnessSQL introduces a harness‑native post‑training framework that keeps the full stateful, multi‑turn interaction structure of real‑world database agents during both supervised fine‑tuning and reinforcement learning. By building isolated executable database environments with hidden execution oracles and retaining only verified trajectories for full‑sequence SFT, the method enables execution‑reward RL that aligns training with inference. Experiments on Spider 2.0‑SQLite show dramatic gains in execution accuracy for compact models, and the approach transfers effectively to out‑of‑distribution interactive benchmarks such as BIRD‑Interact and LiveSQLBench.
By Haolin Yang, Jipeng Zhang, Jian Xie, Shuaishuai Gong, Sirui Han, Yike Guo
arXiv:2607. 06799v1 Announce Type: cross Abstract: Evaluating uncertainty in AI-generated SQL queries requires estimating whether a query is correct, where correct means it executes to the same result as a human-written reference.
By Robert Richardson
arXiv:2607. 06229v1 Announce Type: cross Abstract: Major cloud data platforms now expose large language model capabilities as native SQL functions, enabling analysts to perform classification, filtering, sentiment analysis, extraction, similarity search, and aggregation within ordinary SQL queries.
By Tianyang Liu, Canwen Xu, Fangyu Lei, Nikki Lijing Kuang, Jixuan Chen, Tao Yu, Julian McAuley, Zhewei Yao, Yuxiong He
Self-evolving language models have recently emerged as a promising path toward superintelligence, with the advantage of reducing the cost of human supervision. While considerable progress has been mad...
Self-Play Search Distillation (SPSD) is a framework that generates superhuman synthetic data by having MuZero-like networks play board games in executable environments. The search records are converted into structured reasoning chains that serve as environment‑grounded supervision for training large language models. When applied to Qwen3‑4B‑Base, SPSD improves performance on six mathematics benchmarks from 24.1 to 36.6 and raises the win rate on unseen games from 15% to 45%.
By Lorenzo Molfetta, Wai-Chung Kwan, Giacomo Frisoni, Luca Ragazzi, Gianluca Moro, Pavlos Vougiouklis, Jeff Z. Pan, Pasquale Minervini
J-Zero introduces a unified Challenger–Solver–Judge co‑evolution framework that enables self‑improvement of language models without requiring external supervision. The Challenger generates increasingly difficult tasks, the Solver learns to produce better responses, and the Judge adapts using preference pairs derived from the Solver’s own outputs rather than from its own scores. Experiments show J‑Zero outperforms baselines by an average of 4.2 points on verifiable tasks and 8.0 points on unverifiable tasks, maintaining improvement over ten iterations while baselines degrade after two.
By Gyouk Chu, Myeongho Jeon, Eunho Yang