CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation

• URL: http://arxiv.org/abs/2605.08057v1
• Date: Fri, 08 May 2026 17:44:15 GMT
• Title: CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
• Abstract summary: Current Text-to-BIRD solutions struggle to perform well on the most challenging tasks in the Bird-Bench benchmark.<n>This is due to inadequate solution space exploration.<n>We present a novel Text-to-BIRD pipeline that dynamically scale the breadth of the exploration for generating solution candidates.<n>Our solution achieves a state-of-the-art score of 51.72% on the "challenging" tier of BIRD development set problems.
• Score: 6.312008949668287
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While recent advancements in inference-time learning have improved LLM reasoning on Text-to-SQL tasks, current solutions still struggle to perform well on the most challenging tasks in the Bird-Bench (BIRD) benchmark. This is due to inadequate solution space exploration, which is necessary to uncover promising candidate queries that can be further refined to produce the correct output. To address this challenge, we introduce CA-SQL, a novel Text-to-SQL pipeline that utilizes the estimated difficulty of a task to dynamically scale the breadth of the exploration for generating solution candidates. In addition, we use a custom prompt seeding method, based on principles of evolutionary search, to further elicit exploratory behavior from the base LLM and a novel voting method to select the best candidate solution at the end of the search. Experiments demonstrate that our solution achieves a state-of-the-art score of 51.72% on the "challenging" tier of BIRD development set problems, using only GPT-4o-mini, out-performing other in-context learning approaches, even those that leverage larger models. Overall, our method attains a competitive 61.06% execution accuracy and 68.77% Soft F1 score on the BIRD development dataset.

Related papers

• Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding [59.60915947702282]
  Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs)<n>Existing RLVR methods often suffer from exploration inefficiency due to mismatches between the training data's difficulty and the model's capability.<n>We propose SEELE, a novel supervision-aided RLVR framework that dynamically adjusts problem difficulty to stay within the high-efficiency region.
  arXiv  Detail & Related papers  (2025-09-08T17:36:21Z)
• 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)
• SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications [42.04389915459889]
  We introduce BIRDCRITIC, a new benchmark for resolution of complexsql issues.<n>We also present SixGym, a training environment for elevating open-source model capabilities.<n>We integrate these components into an open-source agent, BirdFixer-2.5-14B.
  arXiv  Detail & Related papers  (2025-06-23T09:41:37Z)
• RAISE: Reasoning Agent for Interactive SQL Exploration [47.77323087050061]
  We propose a novel framework that unifies schema linking, query generation, and iterative refinement within a single, end-to-end component.<n>Our method emulates how humans answer questions when working with unfamiliar databases.
  arXiv  Detail & Related papers  (2025-06-02T03:07:08Z)
• TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs [50.820065021136024]
  DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs)<n>Recent methods have attempted to replicate R1's reasoning capabilities in multimodal settings.<n>We propose TACO, a novel reinforcement learning algorithm for visual reasoning.
  arXiv  Detail & Related papers  (2025-05-27T06:30:48Z)
• PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL [54.304872649870575]
  Large Language Models (LLMs) have emerged as powerful tools for Text-to-sense tasks. In this study, we propose that employing query group partitioning allows LLMs to focus on learning the thought processes specific to a single problem type.
  arXiv  Detail & Related papers  (2024-09-21T09:33:14Z)
• Navigating the Labyrinth: Evaluating LLMs' Ability to Reason About Search Problems [62.76627483915117]
  Large Language Models (LLMs) have recently achieved impressive performance in math and reasoning benchmarks.<n>We introduce a new benchmark, SearchBench, which contains 11 unique search problems inspired by intuitive puzzles.<n>We show that using step-by-step, language-only reasoning, even the most advanced LLMs fail to solve SearchBench.
  arXiv  Detail & Related papers  (2024-06-18T00:44:58Z)
• MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation [10.726734105960924]
  Large language models (LLMs) have enabled in-context learning (ICL)-based methods that significantly outperform fine-tuning approaches for text-to- tasks. This study considers the sensitivity of LLMs to the prompts and introduces a novel approach that leverages multiple prompts to explore a broader search space for possible answers. We establish a new SOTA performance on the BIRD in terms of both the accuracy and efficiency of the generated queries.
  arXiv  Detail & Related papers  (2024-05-13T04:59:32Z)
• Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation [76.76046657162306]
  Large language models (LLMs) have emerged as a new paradigm for Text-to- task. Large language models (LLMs) have emerged as a new paradigm for Text-to- task.
  arXiv  Detail & Related papers  (2023-08-29T14:59:54Z)
• JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning [58.71541261221863]
  Join order selection (JOS) is the problem of ordering join operations to minimize total query execution cost. We present JoinGym, a query optimization environment for bushy reinforcement learning (RL) Under the hood, JoinGym simulates a query plan's cost by looking up intermediate result cardinalities from a pre-computed dataset.
  arXiv  Detail & Related papers  (2023-07-21T17:00:06Z)
• DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction [7.388002745070808]
  We study how breaking down the generation problem into sub-problems and feeding the solutions of those sub-problems into Large Language Models can be effective. Our approach with in-context learning beats many heavily fine-tuned models by at least 5%.
  arXiv  Detail & Related papers  (2023-04-21T15:02:18Z)

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.