Residual Skill Optimization for Text-to-SQL Ensembles

Jiongli Zhu; Haoquan Guan; Parjanya Prajakta Prashant; Nikki Lijing Kuang; Seyedeh Baharan Khatami; Canwen Xu; Xiaodong Yu; Yingyu Lin

cs.CLMay 20, 2026

Residual Skill Optimization for Text-to-SQL Ensembles

Authors: Jiongli Zhu, Haoquan Guan, Parjanya Prajakta Prashant, Nikki Lijing Kuang, Seyedeh Baharan Khatami, Canwen Xu, Xiaodong Yu, Yingyu Lin, +3 more

Organizations: University of California, San Diego · 2Snowflake AI Research

Abstract

Text-to-SQL ensembles improve over single-candidate generation by drawing multiple SQL candidates and selecting one, but their effectiveness is bounded by Pass@K, the probability that at least one of K candidates is correct. Existing methods source diversity heuristically through stochastic decoding or prompt variants, leaving candidate sets dominated by correlated failures. We present DivSkill-SQL, a residual skill optimization framework that builds complementary agentic Text-to-SQL ensembles without model fine-tuning: each new skill is optimized on examples the current skill ensemble fails on, provably targeting its marginal contribution to Pass@K. On Spider2-Lite, DivSkill-SQL improves selected accuracy by up to +11.1 points on Snowflake and +8.3 on BigQuery over the strongest ensemble baseline, with consistent gains across two base models (Opus-4.6 and GPT-5.4). Skills optimized on a single dialect transfer without retraining across dialects (Snowflake, BigQuery, SQLite) and to a different task formulation, such as BIRD-Critic (+2.6 pts). Error diagnostics show up to 3x fewer hallucinated schema references and function calls, indicating that gains come from genuinely reliable complementary skills rather than surface-form variation.

Explore similar work

DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning
Sep 16, 2026Shijie Chen, Yu Gan, Yeounoh Chung +6Text-To-Sql Sql
ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL
Jun 4, 2026Xiaobing Chen, Ai Jian, Eryu Guo +1Text-To-Sql Schema
R $^3$ -SQL: Ranking Reward and Resampling for Text-to-SQL
Apr 28, 2026Hojae Han, Yeonseok Jeong, Seung-won Hwang +2Text-To-Sql Sql

Sep 16, 2026 · cs.CLJ/K move · Enter open · S save

DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning

Shijie Chen, Yu Gan, Yeounoh Chung, Jiani Zhang+5

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 each task, failing to leverage the synergy between these interrelated tasks. In this work, we propose DualSQL, a new Text-to-SQL system consisting of two agents powered by a single model backbone. The agents share the same model weights and agentic scaffold, enabling joint optimization through a robust multi-agent reinforcement learning (RL) framework. We design three database access tools to facilitate effective multi-step reasoning grounded to interactions with the databases. To improve training and avoid model collapse, we introduce a set of rollout guardrail mechanisms that stabilizes multi-agent RL training, supporting DualSQL to keep improving during training. We also introduce a new SQL correctness metric, robust execution match (REX), to more accurately judge SQL correctness and assign reward signals. Being trained on only 3755 examples, DualSQL-4B achieves an impressive 68.0% execution accuracy on the BIRD development set, matching previous 7B models. DualSQL-8B further improves to 71.1%, outperforming previous state-of-the-art single-model solutions with 32B parameters. These results demonstrate the strength of joint multi-agent reinforcement learning for building high performance Text-to-SQL pipelines.

Text-To-Sql Sql Natural Language Queries Large Language Model Baselines Multi-Agent Reinforcement Learning

Open paper Ask about it PDF

Abstract

Explore similar work

DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning

ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL

R3^33-SQL: Ranking Reward and Resampling for Text-to-SQL

R $^3$ -SQL: Ranking Reward and Resampling for Text-to-SQL