DualSQL is a Text-to-SQL system that uses two agents sharing a single model backbone, enabling joint optimization via multi-agent reinforcement learning. The approach incorporates three database access tools for multi-step reasoning, rollout guardrails to stabilize training, and a new SQL correctness metric called robust execution match (REX). Trained on only 3,755 examples, DualSQL-4B reaches 68.0% execution accuracy on the BIRD dev set, while DualSQL-8B achieves 71.1%, surpassing prior state‑of‑the‑art single‑model solutions with 32B parameters.
By Shijie Chen, Yu Gan, Yeounoh Chung, Jiani Zhang, Quannan Li, Sravan Babu Bodapati, Cody J. Greer, Yu Su, Fatma Ozcan
State-of-the-art Text-to-SQL systems are typically multi-agent pipelines centered around two fundamental tasks: schema linking and SQL generation. However, existing work trains separate models for eac...
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: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:2606. 06825v1 Announce Type: cross Abstract: Reinforcement learning has recently shown promise in improving large language models for Text-to-SQL generation, yet existing methods typically optimize one-shot rewards defined over a single SQL state.
By Shihao Zhang, Xiaoman Wang, Yuan Liu, Yunshi Lan, Weining Qian
arXiv:2609.20842v1 Announce Type: new
Abstract: Text-to-SQL translates natural-language questions into executable SQL queries, but open-source large language models still require task-specific post-t...
By Qifeng Cai, Xuanguang Pan, Hao Liang, Chang Xu, Wentao Zhang
arXiv:2608. 09168v1 Announce Type: new Abstract: Agent skills are increasingly used to equip large language model (LLM) agents with reusable procedural knowledge.
By Liang He, Jingbo Wen, Hongyu Gu, Hao Li, Haoyu Wang, Yixiong Chen, Kangning Cui, Xilu Wang
arXiv:2505. 04671v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) trained with reinforcement learning (RL) have improved Text-to-SQL performance.
By Yuxin Zhang, Meihao Fan, Ju Fan, Mingyang Yi, Yuyu Luo, Guoliang Li, Bin Wu, Wenchao Zhou
arXiv:2607. 23263v1 Announce Type: new Abstract: Deciding whether a trajectory actually fulfills its instruction governs how we measure computer-use agents on long-horizon graphical-user-interface tasks and how we train them with reinforcement learning.
By Yang Wan, Zhenhao Zhang, Jierui Wang, Linchao Zhu
SQL-Zero is a self‑playing framework that trains a Text‑to‑SQL agent without any human‑annotated natural‑language/SQL pairs. It uses a challenger and a solver, both based on the same large language model, to generate SQL queries that are only validated by execution against the database. On the BIRD dataset, self‑play improves performance over a zero‑shot baseline by 6.6 to 7.3 points and shows promising transfer to unseen Spider databases, especially at 3B parameter scale.
By Daniel Machado Pedrozo, Julia Soares Dollis, Bryan Lincoln Marques de Oliveira, Vinicius Alboneti Aguiar, S\'avio Salvarino Teles de Oliveira, Telma Woerle de Lima Soares
TRUST‑SQL tackles Text‑to‑SQL parsing in environments where the full database schema is unknown, a common scenario in enterprise settings with many noisy tables. The method models the problem as a Partially Observable Markov Decision Process and uses a four‑phase protocol to verify only relevant metadata, guided by a Dual‑Track GRPO strategy that separates exploration from execution rewards. Experiments on five benchmarks show significant gains, with the 4B and 8B variants outperforming base models by 30.6% and 16.6% respectively, while matching or exceeding baselines that rely on pre‑loaded schemas.
By Ai Jian, Xiaoyun Zhang, Eryu Guo, Wanrou Du, Jingqing Ruan, Jiangbo Pei, Weipeng Zhang, Ke Zeng, Xunliang Cai
arXiv:2608. 12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment.
By Haoze Wu, Chuqiao Kuang, Tianyi Zhuang, Xiaoguang Li