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

• URL: http://arxiv.org/abs/2606.17821v1
• Date: Tue, 16 Jun 2026 11:48:50 GMT
• Title: DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL
• Abstract summary: DecoSearch is a training-free framework that routing each query to the appropriate level of reasoning effort.<n>It achieves 70.53% execution accuracy on BIRD and 88.31% on Spider with a DeepSeek backbone.
• Score: 21.568773170643084
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning Problems [56.24850338895714]
  RAG struggles with textbfexploratory reasoning problems (ERPs) that are the complex queries involving high uncertainty and ambiguity.<n>We introduce emphPlanRAG, an RAG framework that modelsERPs of natural language as textbflogical query trees (LQTs).<n>PlanRAG outperforms state-of-the-art iteration-based and graph-based RAG systems on our newly constructed dataset, textbfWikiWeb-ERP.
  arXiv  Detail & Related papers  (2026-07-01T06:43:55Z)
• LEAF-SQL: Level-wise Exploration with Adaptive Fine-graining for Text-to-SQL Skeleton Prediction [4.626100354811136]
  LEAF- is a novel framework that reframes skeleton prediction as a coarse-to-fine tree search process.<n>Our method achieves 71.6 execution accuracy, which outperforms leading search-based and skeleton-based methods.
  arXiv  Detail & Related papers  (2026-05-10T03:43:29Z)
• EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement [10.675982676332941]
  Existing approaches treat schemas as fixed and address errors downstream.<n>We frame schema refinement as a constrained optimization problem.<n>We analyze the computational hardness of this problem, which motivates a column-wise greedy decomposition.
  arXiv  Detail & Related papers  (2026-05-01T13:01:59Z)
• ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering [55.55968342644846]
  Table serialization remains a critical bottleneck for Large Language Models (LLMs) in complex table question answering.<n>Existing serialization methods fail to capture explicit hierarchies and lack schema flexibility.<n>We propose ASTRA (Adaptive Semantic Tree Reasoning Architecture) including two main modules, AdaSTR and DuTR.<n> Experiments on complex table benchmarks demonstrate that our method achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2026-04-10T06:09:41Z)
• Agentic DAG-Orchestrated Planner Framework for Multi-Modal, Multi-Hop Question Answering in Hybrid Data Lakes [5.276278723196607]
  Agentic DAG-Orchestrated Transformer (A.DOT) Planner is a framework for multi-modal, multi-hop question answering.<n>A.DOT compiles user NL queries into directed acyclic graph (DAG) execution plans spanning both structured and unstructured stores.<n>System decomposes queries into parallelizable sub-queries, incorporates schema-aware reasoning, and applies both structural and semantic validation.
  arXiv  Detail & Related papers  (2026-03-15T05:34:16Z)
• SQuARE: Structured Query & Adaptive Retrieval Engine For Tabular Formats [0.0]
  SQuARE is a hybrid retrieval framework with sheet-level, complexity-aware routing.<n>It computes a continuous score based on header depth and merge density.<n>SQuARE consistently surpasses single-strategy baselines and ChatGPT-4o on both retrieval precision and end-to-end answer accuracy.
  arXiv  Detail & Related papers  (2025-12-03T22:11:45Z)
• Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation [54.53145282349042]
  We introduce DSR-sourced, a textbfDual-textbfS textbfReasoning framework that models Text-to-context as an interaction between an adaptive context state and a progressive generation state.<n>Without any post-training or in-context examples, DSR-sourced achieves competitive performance, reaching 35.28% execution accuracy on Spider 2.0-Snow and 68.32% on BIRD development set.
  arXiv  Detail & Related papers  (2025-11-26T13:52:50Z)
• Reasoning-enhanced Query Understanding through Decomposition and Interpretation [87.56450566014625]
  ReDI is a Reasoning-enhanced approach for query understanding through Decomposition and Interpretation.<n>We compiled a large-scale dataset of real-world complex queries from a major search engine.<n> Experiments on BRIGHT and BEIR demonstrate that ReDI consistently surpasses strong baselines in both sparse and dense retrieval paradigms.
  arXiv  Detail & Related papers  (2025-09-08T10:58:42Z)
• SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction [13.793886767052905]
  In-context learning and chain-of-thought can be utilized to develop a robust solution for text-to-context systems.<n>We propose a multi-agent framework that decomposes the Text2 task into schema linking, subproblem identification, query plan generation, and a guided correction loop.
  arXiv  Detail & Related papers  (2025-08-30T18:27:12Z)
• UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification [50.59009084277447]
  We introduce UNJOIN, a framework that decouples the retrieval of schema elements from logic generation.<n>In the first stage, we merge the column names of all tables in the database into a single-table representation by prefixing each column with its table name.<n>In the second stage, the query is generated on this simplified schema and mapped back to the original schema by reconstructing JOINs, UNIONs, and relational logic.
  arXiv  Detail & Related papers  (2025-05-23T17:28:43Z)
• RSL-SQL: Robust Schema Linking in Text-to-SQL Generation [51.00761167842468]
  We propose a novel framework called RSL- that combines bidirectional schema linking, contextual information augmentation, binary selection strategy, and multi-turn self-correction. benchmarks demonstrate that our approach achieves SOTA execution accuracy among open-source solutions, with 67.2% on BIRD and 87.9% on GPT-4ocorrection. Our approach outperforms a series of GPT-4 based Text-to-Seek systems when adopting DeepSeek (much cheaper) with same intact prompts.
  arXiv  Detail & Related papers  (2024-10-31T16:22:26Z)
• Improving One-stage Visual Grounding by Recursive Sub-query Construction [102.47477888060801]
  We improve one-stage visual grounding by addressing current limitations on grounding long and complex queries. We show our new one-stage method obtains 5.0%, 4.5%, 7.5%, 12.8% absolute improvements over the state-of-the-art one-stage baseline.
  arXiv  Detail & Related papers  (2020-08-03T17:43:30Z)

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.