mlsanityData to 14 Oct 2026

Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation

arXiv 2511.21402 ↗First posted 26 Nov 2025cs.CLcited by 10

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Recent divide-and-conquer reasoning approaches, particularly those based on Chain-of-Thought (CoT), have substantially improved the Text-to-SQL capabilities of Large Language Models (LLMs). However, when applied to complex enterprise databases, such methods struggle to maintain coherent reasoning due to limited context capacity, unreliable schema linking, and weak grounding in database semantics. To overcome these issues, we introduce DSR-SQL, a Dual-State Reasoning framework that models Text-to-SQL as an interaction between an adaptive context state and a progressive generation state. The first constructs a compact, semantically faithful environment by refining large schemas and selecting relevant structures, while the second formalizes SQL synthesis as feedback-guided state transitions, enabling the model to self-correct and align with user intent. Without any post-training or in-context examples, DSR-SQL achieves competitive performance, reaching 35.28% execution accuracy on Spider 2.0-Snow and 68.32% on BIRD development set. Our implementation will be open-sourced at: https://github.com/DMIRLAB-Group/DSR-SQL.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 25 of its 31 references that are in the map. First posted on arXiv 26 Nov 2025.

Builds on

25 of 31 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL31 May
  2. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL22 May
  3. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL2 Oct

Other references · 22

  1. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  2. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
  3. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 232
  4. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  5. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 164
  6. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 164
  7. 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 119
  8. 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 105
  9. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 91
  10. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  11. 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 53
  12. 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 52
10 more
  1. 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 52
  2. 2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
  3. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Explorationcited by 37
  4. 2025Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Searchcited by 34
  5. 2025Automatic Metadata Extraction for Text-to-SQLcited by 27
  6. 2017An Encoder-Decoder Framework Translating Natural Language to Database Queriescited by 23
  7. 2024MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQLcited by 22
  8. 2023Reboost Large Language Model-based Text-to-SQL, Text-to-Python, and Text-to-Function -- with Real Applications in Traffic Domaincited by 9
  9. 2025A State-of-the-Art SQL Reasoning Model using RLVRcited by 5
  10. 2025Text-to-SQL for Enterprise Data Analyticscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 10.

10 papers.

  1. 2026APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQLcited by 8
  2. 2026FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agentscited by 4
  3. 2026AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Viewscited by 1
  4. 2026EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQLcited by 1
  5. 2026ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQLcited by 0
  6. 2026Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agentscited by 0
  7. 2026Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflowscited by 0
  8. 2026DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generationcited by 0
  9. 2026Iteration Without Elaboration: A Simple ReAct Architecture Suffices for Text-to-SQL Generationcited by 0
  10. 2026ARCS: Towards Precise Text-to-SQL via Structured Disambiguationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning
  2. 2025BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation
  3. 2025ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQL
  4. 2025DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL
  5. 2024Multi-Turn Interactions for Text-to-SQL with Large Language Models
  6. 2025RAISE: Reasoning Agent for Interactive SQL Exploration
  7. 2026IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Models
  8. 2025Rethinking Agentic Workflows: Evaluating Inference-Based Test-Time Scaling Strategies in Text2SQL Tasks