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

• URL: http://arxiv.org/abs/2606.05906v1
• Date: Thu, 04 Jun 2026 09:11:04 GMT
• Title: ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL
• Abstract summary: Existing methods either rely on full-schema generation, or use a separate retriever trained with static gold-column supervision, whose targets may be suboptimal for the current generator policy.<n>We propose ACE-optimization, a reinforcement learning framework that jointly optimize schema retrieval andsql generation under execution feedback.<n>With approximately 3k Text-to-question-Database pairs for RL training, ACE- achieves 65.3% greedy execution accuracy on BIRD Dev while using 0.93k output tokens per query.
• Score: 6.968226996634463
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-SQL maps natural language questions to executable SQL queries. Modern databases often contain large and complex schemas, making schema linking a critical step for accurate SQL generation. Existing methods either rely on full-schema generation, which leaves schema linking implicit within a large search space, or use a separate retriever trained with static gold-column supervision, whose targets may be suboptimal for the current generator policy. To address this issue, we propose Adaptive Co-optimization via Empirical Credit Assignment for Text-to-SQL (ACE-SQL), a reinforcement learning (RL) framework that jointly optimizes schema retrieval and SQL generation under execution feedback. ACE-SQL constructs an online column-set pool from generator rollouts and derives adaptive on-policy retrieval targets from the column set most frequently associated with execution-correct rollouts. This induces bidirectional adaptation, where the retriever adapts toward column sets that the generator can execute correctly, while the generator adapts to the retriever's evolving schema selections under execution feedback. With approximately 3k synthetic Text-to-SQL question-database pairs for RL training, ACE-SQL achieves 65.3% greedy execution accuracy on BIRD Dev while using 0.93k output tokens per query. The repository is available at https://github.com/xbchen1/ACE-SQL.

Related papers

• DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation [11.797290397638962]
  This paper develops textscDexter, a prompting/non-fine-tuning text-based system for complex questions.<n>textscDexter achieves higher accuracy compared to the state-of-the-art using both open-source/weight models.
  arXiv  Detail & Related papers  (2026-08-12T10:17:08Z)
• DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL [21.568773170643084]
  DecoSearch is a training-free framework that routing each query to the appropriate level of reasoning effort.<n>It achieves 70.53% execution accuracy on BIRD and 88.31% on Spider with a DeepSeek backbone.
  arXiv  Detail & Related papers  (2026-06-16T11:48:50Z)
• EvoSQL: Memory-Augmented Critic-Generator Co-Evolution for Text-to-SQL [12.094895321584152]
  Evowen is a co-evolution of an interaction between a generator and a critic.<n>To strengthen the generator-critic pair, we introduce a Self-Distillation Policy (SDPO)<n>Experiments show that Evowen consistently improves open-source models over Maj@16 baselines.
  arXiv  Detail & Related papers  (2026-06-04T14:21:19Z)
• 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)
• Track-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQL [50.84251174559123]
  Generative language models' performance does not extend equivalently to multi-turn Text-to-sourced.<n>We propose Track-, which enhances generative language models with dual-extractive modules designed to track schema and contextual changes in multi-turn Text-to-sourced.<n>Track- significantly improves execution accuracy in multi-turn interactions by 7.1% and 9.55% on datasets, respectively.
  arXiv  Detail & Related papers  (2026-03-06T07:57:06Z)
• 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)
• From Queries to Insights: Agentic LLM Pipelines for Spatio-Temporal Text-to-SQL [8.496933324334167]
  We present a naive text-to-Act baseline (Rellama-sqlcoder-8b) with orchestration by a Mistral-based Rellama-sqlcoder-8b.<n>We evaluate on 35 natural-language queries over the NYC and Tokyo check-in, covering spatial, temporal multi-dataset reasoning.<n>The agent achieves substantially higher accuracy than the dataset 91.4% vs. 28.6% and enhances usability through maps, and plots structured natural-language summaries.
  arXiv  Detail & Related papers  (2025-10-29T22:18:57Z)
• CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation [1.169202600932732]
  We introduce Cogni-R1-Zero, a reinforcement learning (RL) framework and model.<n>We use a lightweight reward signal based on execution correctness and format-tag compliance.<n>Our method achieves state-of-the-art execution accuracy on Text2 benchmark.<n>To support further research in efficient and interpretable Text-to-code modeling, we release two curated datasets.
  arXiv  Detail & Related papers  (2025-07-08T14:17:07Z)
• 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)
• E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL [1.187832944550453]
  We introduce E-Seek, a novel pipeline specifically designed to address these challenges through direct schema linking and candidate predicate augmentation.<n>E-Seek enhances the natural language query by incorporating relevant database items (i.e., tables, columns, and values) and conditions directly into the question andsql construction plan, bridging the gap between the query and the database structure.<n> Comprehensive evaluations illustrate that E-Seek achieves competitive performance, particularly excelling in complex queries with a 66.29% execution accuracy on the test set.
  arXiv  Detail & Related papers  (2024-09-25T09:02:48Z)
• Benchmarking and Improving Text-to-SQL Generation under Ambiguity [25.283118418288293]
  We develop a novel benchmark called AmbiQT where each text is interpretable as two plausible SQLs due to lexical and/or structural ambiguity. We propose LogicalBeam, a new decoding algorithm that navigates thesql logic space using a blend of plan-based template generation and constrained infilling.
  arXiv  Detail & Related papers  (2023-10-20T17:00:53Z)
• SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended) [53.95151604061761]
  This paper introduces the framework for enhancing Text-to- filtering using large language models (LLMs) With few-shot prompting, we explore the effectiveness of consistency decoding with execution-based error analyses. With instruction fine-tuning, we delve deep in understanding the critical paradigms that influence the performance of tuned LLMs.
  arXiv  Detail & Related papers  (2023-05-26T21:39:05Z)
• UNITE: A Unified Benchmark for Text-to-SQL Evaluation [72.72040379293718]
  We introduce a UNIfied benchmark for Text-to-domain systems. It is composed of publicly available text-to-domain datasets and 29K databases. Compared to the widely used Spider benchmark, we introduce a threefold increase in SQL patterns.
  arXiv  Detail & Related papers  (2023-05-25T17:19:52Z)

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.