ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL
In Text-to-SQL, execution feedback is essential for guiding large language models (LLMs) to reason accurately and generate reliable SQL queries. However, existing methods treat execution feedback solely as a post-hoc signal for correction or selection, failing to integrate it into the generation process. This limitation hinders their ability to address reasoning errors as they occur, ultimately reducing query accuracy and robustness. To address this issue, we propose ReEx-SQL (Reasoning with Execution-Aware Reinforcement Learning), a framework for Text-to-SQL that enables models to interact with the database during decoding and dynamically adjust their reasoning based on execution feedback. ReEx-SQL introduces an execution-aware reasoning paradigm that interleaves intermediate SQL execution into reasoning paths, facilitating context-sensitive revisions. It achieves this through structured prompts with markup tags and a stepwise rollout strategy that integrates execution feedback into each stage of generation. To supervise policy learning, we develop a composite reward function that includes an exploration reward, explicitly encouraging effective database interaction. Additionally, ReEx-SQL adopts a tree-based decoding strategy to support exploratory reasoning, enabling dynamic expansion of alternative reasoning paths. Notably, ReEx-SQL achieves 88.8% on Spider and 64.9% on BIRD at the 7B scale, surpassing the standard reasoning baseline by 2.7% and 2.6%, respectively. It also shows robustness, achieving 85.2% on Spider-Realistic with leading performance. In addition, its tree-structured decoding improves efficiency and performance over linear decoding, reducing inference time by 51.9% on the BIRD development set.
Code (0)
등록된 구현이 없습니다.
Tasks
Text to SQLText-To-SQLSimilar Papers 제목 키워드 기반
MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL
As large language models (LLMs) are increasingly used in Text-to-SQL tasks, Reinforcement Learning (RL) has become a common method for improving performance. Existing methods primarily rely on static execution feedback, …
Reinforcement LearningReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay
Embodied exploration is a target-driven process that requires embodied agents to possess fine-grained perception and knowledge-enhanced decision making. While recent attempts leverage MLLMs for exploration due to their s…
Reinforcement LearningDecision MakingWhen Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making
Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning, planning, and decision-making during interactions with the environment. However, invoking LLM reasoni…
Reinforcement LearningStepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning
Existing code reasoning methods primarily supervise final code outputs, ignoring intermediate states, often leading to reward hacking where correct answers are obtained through inconsistent reasoning. We propose StepCode…
Reinforcement LearningCode GenerationSemantic Reasoning from Model-Agnostic Explanations
With the wide adoption of black-box models, instance-based \emph{post hoc} explanation tools, such as LIME and SHAP became increasingly popular. These tools produce explanations, pinpointing contributions of key features…
model