DecoSearch: 复杂度感知路由与计划级修复提升Text-to-SQL

在BIRD上达到70.53%执行准确率，在Spider上达88.

31%，使用DeepSeek作为骨干模型，比训练无关基线消耗少一个数量级的token。该方法还可作为模型无关包装器，一致提升微调后的SQL生成骨干性能。

DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL

Large Language Models (LLMs) have demonstrated remarkable capabilities in translating natural language to SQL, yet existing methods still falter on complex queries requiring multi-step, data-aware reasoning. We introduce DecoSearch, a training-free framework that addresses this by routing each query to the appropriate level of reasoning effort. A lightweight Schema Selector first prunes the full database schema to the relevant tables and columns. An LLM Judger then decides whether the question requires decomposition: straightforward questions follow a direct generation path and complex ones are escalated to a Directed Acyclic Graph (DAG) of atomic sub-questions, each solved by a targeted SQL generation step. A RAG component grounds the decomposer with semantically similar training examples, and a Topology Refiner restructures the reasoning plan when execution failures signal a flawed decomposition rather than a fixable SQL error. DecoSearch achieves 70.53% execution accuracy on BIRD and 88.31% on Spider with a DeepSeek backbone, surpassing all training-free baselines while consuming an order of magnitude fewer tokens than competing methods. It also functions as a model-agnostic wrapper, consistently improving fine-tuned SQL generation backbones without any modification to the pipeline.

This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include DecoSearch, DeepSeek, Text-to-SQL, 推理模型.

Primary source verification: published directly by arXiv: DeepSeek with first-party authority.