Residual Skill Optimization for Text-to-SQL Ensembles

• URL: http://arxiv.org/abs/2605.21792v1
• Date: Wed, 20 May 2026 22:36:11 GMT
• Title: Residual Skill Optimization for Text-to-SQL Ensembles
• Abstract summary: We present DivSkill, a residual skill optimization framework that builds complementary agentic Text-to- ensembles without model fine-tuning.<n>Each new skill is optimized on examples the current skill ensemble fails on, provably targeting its marginal contribution to Pass@K.<n>On Spider2-Lite, DivSkill improves selected accuracy by up to +11.1 points on Snowflake and +8.3 on BigQuery over the strongest ensemble baseline.<n>Skills optimized a single dialect transfer without retraining across dialects (Snowflake, BigQuery, pts) and to a different task formulation, such as BIRD-Critic (+2.6)
• Score: 37.13373780149542
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows [54.49251107006261]
  We introduce Spider 2.0-AIFunc, a benchmark of 465 verified instances across 125 real-world databases covering six types of AI functions on the Snowflake platform.<n>We find that the strongest proprietary models reach 67-70% execution accuracy while the best open-source model achieves 58.1%.
  arXiv  Detail & Related papers  (2026-07-07T12:54:08Z)
• ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQL [51.98164069124653]
  ProSPy is a Profiling-driven framework for enterprise-scale Text-to-gnostic analysis.<n>ProSPy structures the reasoning process into four stages.<n>It first extracts fine-grained data evidence through automatic profiling.<n>It prunes large schemas into task-relevant contexts.
  arXiv  Detail & Related papers  (2026-06-04T08:13:05Z)
• SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback [26.80964126227997]
  Text-to-on complex schemas is unreliable on a single pass, so recent systems generate multiplesql candidates and let voting filter out errors.<n>Voting alone is not enough, because the multi-candidate recipe has three coupled weaknesses.<n>We present SIRIUS--32B, which addresses all three weaknesses.
  arXiv  Detail & Related papers  (2026-05-31T13:59:09Z)
• FINER-SQL: Boosting Small Language Models for Text-to-SQL [40.19592881059662]
  Large language models suffer from high computational cost, long latency, and data privacy concerns.<n>A natural alternative is to use small language models, which enable efficient and private on-premise deployment.<n>We propose FINER-sql, a scalable and reusable reinforcement learning framework.
  arXiv  Detail & Related papers  (2026-05-05T07:51:29Z)
• R$^3$-SQL: Ranking Reward and Resampling for Text-to-SQL [55.967050404665606]
  R$3$- achieves 75.03 execution accuracy on BIRD-dev, a new state of the art among methods using models with disclosed sizes, with consistent gains across five benchmarks.
  arXiv  Detail & Related papers  (2026-04-28T07:40:50Z)
• CORE-T: COherent REtrieval of Tables for Text-to-SQL [91.76918495375384]
  CORE-T is a scalable, training-free framework that enriches tables with purpose metadata and pre-computes a lightweight table-compatibility cache.<n>Across Bird, Spider, and MMQA, CORE-T improves table-selection F1 by up to 22.7 points while retrieving up to 42% fewer tables.
  arXiv  Detail & Related papers  (2026-01-19T14:51:23Z)
• Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation [54.53145282349042]
  We introduce DSR-sourced, a textbfDual-textbfS textbfReasoning framework that models Text-to-context as an interaction between an adaptive context state and a progressive generation state.<n>Without any post-training or in-context examples, DSR-sourced achieves competitive performance, reaching 35.28% execution accuracy on Spider 2.0-Snow and 68.32% on BIRD development set.
  arXiv  Detail & Related papers  (2025-11-26T13:52:50Z)
• RetrySQL: text-to-SQL training with retry data for self-correcting query generation [1.6707278580444538]
  We introduce Retry, a new approach to training text-to-generation models.<n>We demonstrate that retry steps yield an improvement of up to 4 percentage points in both overall and challenging execution accuracy metrics.
  arXiv  Detail & Related papers  (2025-07-03T11:00:49Z)
• ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback [49.21833666405111]
  Large language models (LLMs) excel in many reasoning tasks, but their ability to leverage Chain-of-Thought (CoT) reasoning remains underexplored.<n>We propose ExCoT, a novel framework that iteratively optimize open-source LLMs by combining CoT reasoning with off-policy and on-policy DPO.
  arXiv  Detail & Related papers  (2025-03-25T18:17:36Z)
• SQLCritic: Correcting Text-to-SQL Generation via Clause-wise Critic [8.680252929322684]
  We introduce a clause-wise critique generation task along with a benchmark,sqlCriticBench, which performs fine-grained error localization.<n>We also propose an automatically training dataset curation pipeline which annotates clause-wise critique at scale.
  arXiv  Detail & Related papers  (2025-03-11T02:52:39Z)
• RSL-SQL: Robust Schema Linking in Text-to-SQL Generation [51.00761167842468]
  We propose a novel framework called RSL- that combines bidirectional schema linking, contextual information augmentation, binary selection strategy, and multi-turn self-correction. benchmarks demonstrate that our approach achieves SOTA execution accuracy among open-source solutions, with 67.2% on BIRD and 87.9% on GPT-4ocorrection. Our approach outperforms a series of GPT-4 based Text-to-Seek systems when adopting DeepSeek (much cheaper) with same intact prompts.
  arXiv  Detail & Related papers  (2024-10-31T16:22:26Z)
• Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead [6.966624873109535]
  State-of-the-art (SOTA) systems use large, pre-trained and finetuned language models, such as the T5-family. With multi-tasking (MT) over coherent tasks with discrete prompts during training, we improve over specialized text-to-three models. We conduct studies to tease apart errors attributable to domain and compositional generalization.
  arXiv  Detail & Related papers  (2023-02-21T23:15:33Z)
• N-Best Hypotheses Reranking for Text-To-SQL Systems [6.966624873109535]
  Text-to- task maps natural language utterances to structured queries. State-of-the-art (SOTA) systems rely on finetuning large, pre-trained language models. Findings show significant potential improvements with reranking.
  arXiv  Detail & Related papers  (2022-10-19T15:35:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.