Reward-SQL: Boosting Text-to-SQL via Stepwise Reasoning and Process-Supervised Rewards

• URL: http://arxiv.org/abs/2505.04671v2
• Date: Sun, 18 May 2025 03:32:19 GMT
• Title: Reward-SQL: Boosting Text-to-SQL via Stepwise Reasoning and Process-Supervised Rewards
• Authors: Yuxin Zhang, Meihao Fan, Ju Fan, Mingyang Yi, Yuyu Luo, Jian Tan, Guoliang Li,
• Abstract summary: External Process Reward Models (PRMs) can be introduced during training to provide fine-grained supervision.<n>We propose Reward-BIRD, a framework that explores how to incorporate PRMs into the Text-to-the- reasoning process effectively.
• Score: 25.810871864483076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in large language models (LLMs) have significantly improved performance on the Text-to-SQL task by leveraging their powerful reasoning capabilities. To enhance accuracy during the reasoning process, external Process Reward Models (PRMs) can be introduced during training and inference to provide fine-grained supervision. However, if misused, PRMs may distort the reasoning trajectory and lead to suboptimal or incorrect SQL generation. To address this challenge, we propose Reward-SQL, a framework that systematically explores how to incorporate PRMs into the Text-to-SQL reasoning process effectively. Our approach follows a "cold start, then PRM supervision" paradigm. Specifically, we first train the model to decompose SQL queries into structured stepwise reasoning chains using common table expressions (Chain-of-CTEs), establishing a strong and interpretable reasoning baseline. Then, we investigate four strategies for integrating PRMs, and find that combining PRM as an online training signal (e.g.,GRPO) with PRM-guided inference (e.g., best-of-N sampling) yields the best results. Empirically, on the BIRD benchmark, Reward-SQL enables models supervised by PRM (7B) to achieve a 13.1% performance gain across various guidance strategies. Notably, our GRPO-aligned policy model based on Qwen2.5-Coder-7B-Instruct achieves 68.9% accuracy on the BIRD development set, outperforming all baseline methods under the same model size. These results demonstrate the effectiveness of Reward-SQL in leveraging reward-based supervision for Text-to-SQL reasoning.

Related papers

• ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs [56.32212611983997]
  We introduce ReasonFlux-PRM, a novel trajectory-aware PRM to evaluate trajectory-response type of reasoning traces.<n>ReasonFlux-PRM incorporates both step-level and trajectory-level supervision, enabling fine-grained reward assignment aligned with structured chain-of-thought data.<n>Our derived ReasonFlux-PRM-7B yields consistent performance improvements, achieving average gains of 12.1% in supervised fine-tuning, 4.5% in reinforcement learning, and 6.3% in test-time scaling.
  arXiv  Detail & Related papers  (2025-06-23T17:59:02Z)
• Discriminative Policy Optimization for Token-Level Reward Models [55.98642069903191]
  Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs)<n>Q-RM explicitly learns token-level Q-functions from preference data without relying on fine-grained annotations.<n>Reinforcement learning with Q-RM significantly enhances training efficiency, achieving convergence 12 times faster than ORM on GSM8K and 11 times faster than step-level PRM on MATH.
  arXiv  Detail & Related papers  (2025-05-29T11:40:34Z)
• DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning [33.574626079343936]
  We introduce DreamPRM, a domain-reweighted training framework for multimodal PRMs.<n>In the lower-level optimization, DreamPRM performs fine-tuning on multiple datasets with domain weights.<n>In the upper-level optimization, the PRM is evaluated on a separate meta-learning dataset.
  arXiv  Detail & Related papers  (2025-05-26T17:20:17Z)
• Beyond the First Error: Process Reward Models for Reflective Mathematical Reasoning [49.21525229904197]
  We propose a novel data annotation method for PRMs specifically designed to score the long CoT reasoning process.<n>We introduce the concepts of Error Propagation and Error Cessation, enhancing PRMs' ability to identify both effective self-correction behaviors and reasoning based on erroneous steps.<n>Our PRM achieves superior performance across various metrics, including search guidance, BoN, and F1 scores.
  arXiv  Detail & Related papers  (2025-05-20T14:12:05Z)
• ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL [21.29343406227956]
  Execution feedback is essential for guiding large language models to reason accurately and generate reliable queries.<n>Existing methods treat execution feedback solely as a post-hoc signal for correction or selection, failing to integrate it into the generation process.<n>We propose ReEx-Reasoning, a framework for Text-to-Reason that enables models to interact with the database during decoding and dynamically adjust their reasoning based on execution feedback.
  arXiv  Detail & Related papers  (2025-05-19T06:46:47Z)
• Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward [15.448159172903138]
  Reinforcement learning (RL) has been widely adopted to enhance the performance of large language models (LLMs) on Text-to- tasks.<n>Existing methods often rely on execution-based or LLM-based Bradley-Terry reward models.<n>We propose a novel Text-to- RL fine-tuning framework named Graph-Reward-Reward, which employs the GMNScore outcome reward model.
  arXiv  Detail & Related papers  (2025-05-18T11:53:01Z)
• Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning [0.12289361708127876]
  This work reframes the Text-to-the-task as a pathway for teaching large language models (LLMs) to reason over and manipulate data.<n>We propose a two-stage framework that teaches a model how to traverse, filter, and aggregate table fields.<n> Empirically, our approach achieves substantial gains on reasoning-intensive datasets such as BIRD and CRT-QA.
  arXiv  Detail & Related papers  (2025-04-23T19:02:04Z)
• Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL [13.215512957681185]
  Existing approaches often rely on handcrafted reasoning paths with inductive biases that can limit their overall effectiveness.<n>Motivated by the recent success of reasoning-enhanced models such as OpenAI o1, we propose a novel set of partial rewards tailored specifically for the Text-to- exploration task.<n>We demonstrate that RL-only training with our proposed rewards consistently achieves higher accuracy and superior generalization compared to supervised fine-tuning.
  arXiv  Detail & Related papers  (2025-03-29T17:29:30Z)
• R-PRM: Reasoning-Driven Process Reward Modeling [53.06844294668382]
  Process Reward Models (PRMs) have emerged as a promising solution by evaluating each reasoning step.<n>Existing PRMs typically output evaluation scores directly, limiting both learning efficiency and evaluation accuracy.<n>We propose Reasoning-Driven Process Reward Modeling (R-PRM)<n>R-PRM generates seed data from limited annotations, effectively bootstrapping our model's reasoning capabilities.
  arXiv  Detail & Related papers  (2025-03-27T09:23:08Z)
• 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)
• VisualPRM: An Effective Process Reward Model for Multimodal Reasoning [76.35753243272521]
  We introduce VisualPRM, which improves the reasoning abilities of existing Multimodal Large Language Models (MLLMs)<n>Our model achieves a 5.9-point improvement across seven multimodal reasoning benchmarks.<n>For the evaluation of multimodal PRMs, we propose VisualProcessBench, a benchmark with human-annotated step-wise correctness labels.
  arXiv  Detail & Related papers  (2025-03-13T12:03:37Z)
• STaR-SQL: Self-Taught Reasoner for Text-to-SQL [20.719165038519744]
  "chain-of-thought" rationales have proven effective for improving the performance of large language models on complex reasoning tasks.<n>Applying such techniques to structured tasks, such as text-to-driven, remains largely unexplored.<n>In this paper, we introduce Self-Taughter for text-to-driven (STaR-), a novel approach that reframes query generation as a reasoning process.<n> Experimental results on the challenging Spider benchmark demonstrate that STaR- significantly improves text-to-performance, achieving an execution accuracy of 86.6%.<n>These findings underscore the potential of reasoning-augmented training for
  arXiv  Detail & Related papers  (2025-02-19T08:58:44Z)
• The Lessons of Developing Process Reward Models in Mathematical Reasoning [62.165534879284735]
  Process Reward Models (PRMs) aim to identify and mitigate intermediate errors in the reasoning processes.<n>We develop a consensus filtering mechanism that effectively integrates Monte Carlo (MC) estimation with Large Language Models (LLMs)<n>We release a new state-of-the-art PRM that outperforms existing open-source alternatives.
  arXiv  Detail & Related papers  (2025-01-13T13:10:16Z)
• Free Process Rewards without Process Labels [55.14044050782222]
  We show that an textitimplicit PRM can be obtained at no additional cost, by simply training an ORM on the cheaper response-level labels.<n>We show that our implicit PRM, when instantiated with the cross-entropy (CE) loss, is more data-efficient and can keep improving generation models even when trained with only one response per instruction.
  arXiv  Detail & Related papers  (2024-12-02T21:20:02Z)
• Let's reward step by step: Step-Level reward model as the Navigators for Reasoning [64.27898739929734]
  Process-Supervised Reward Model (PRM) furnishes LLMs with step-by-step feedback during the training phase. We propose a greedy search algorithm that employs the step-level feedback from PRM to optimize the reasoning pathways explored by LLMs. To explore the versatility of our approach, we develop a novel method to automatically generate step-level reward dataset for coding tasks and observed similar improved performance in the code generation tasks.
  arXiv  Detail & Related papers  (2023-10-16T05:21:50Z)

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.