发表机构
Department of Electrical and Computer Engineering, Seoul National University; AI Center, Samsung Electronics; AIIS, ASRI, INMC, ISRC, and IPAI, Seoul National University（首尔国立大学电气与计算机工程系; 三星电子人工智能中心; 首尔国立大学人工智能研究所、高级科学研究所以及综合纳米技术中心、信息存储研究中心和人工智能平台研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究文本到SQL推理问题，提出AutoThinkSQL框架，集成自动思考机制到SFT和DPO中，使模型能根据查询难度动态调整推理，在基准测试中提升效果，减少输出令牌和延迟，让推理决策与查询难度匹配。
AI 中文摘要
近期文本到SQL的方法严重依赖以推理为中心的范式，如思维链（CoT），在复杂基准测试中有显著提升，但高推理开销。现实中很多查询简单无需多步推导，强制推理浪费。为此提出AutoThinkSQL框架，将自动思考机制集成到文本到SQL的监督微调（SFT）和直接偏好优化（DPO）中。该方法能让模型对简单查询动态绕过推理，对复杂查询调用深度CoT。在Qwen3-Coder-30B-A3B上，相比最佳基线在Spider和BIRD基准测试中均有提升，还减少了输出令牌和延迟。进一步分析表明模型学会使推理决策与查询难度匹配。
英文摘要
Recent Text-to-SQL methods rely heavily on reasoning-centric paradigms such as Chain-of-Thought (CoT), achieving substantial gains on complex benchmarks at the cost of high inference-time overhead. However, a large fraction of real-world queries are simple lookups or aggregations that can be resolved without multi-step deduction, making forced reasoning wasteful. Thus, we propose AutoThinkSQL, a framework that integrates an auto-thinking mechanism into both Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) on Text-to-SQL. Our approach enables the model to dynamically bypass reasoning for simple queries while invoking deep CoT for complex queries. On Qwen3-Coder-30B-A3B, our method achieves consistent gains compared to the best counterpart baseline on both Spider and BIRD benchmarks while simultaneously reducing average output tokens by 24.6% and 18.3%, and average latency by 17.1% and 11.5% compared to CoT-only generation. Further analysis indicates that the model learns to align its reasoning decisions with query difficulty.
Comments8 pages, 5 figures. Model checkpoints are available at https://huggingface.co/autothinksql
