Learning When to Reason for Text-to-SQL via SFT and DPO

AutoThinkSQL, a framework integrating an auto-thinking mechanism into Supervised Fine-Tuning and Direct Preference Optimization for Text-to-SQL, enables dynamic bypassing of reasoning for simple queries while invoking deep Chain-of-Thought for complex ones. On Qwen3-Coder-30B-A3B, the method achieves consistent gains on Spider and BIRD benchmarks while reducing average output tokens by 24.6% and 18.3% and average latency by 17.1% and 11.5% compared to CoT-only generation.

arXiv:2607.22622v1 Announce Type: new Abstract: 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.