mlsanityData to 14 Oct 2026

AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale

arXiv 2511.17190 ↗First posted 21 Nov 2025cs.CL cs.DBcited by 17

Not on the map. Why?

Abstract (arXiv)

For industrial-scale text-to-SQL, supplying the entire database schema to Large Language Models (LLMs) is impractical due to context window limits and irrelevant noise. Schema linking, which filters the schema to a relevant subset, is therefore critical. However, existing methods incur prohibitive costs, struggle to trade off recall and noise, and scale poorly to large databases. We present AutoLink, an autonomous agent framework that reformulates schema linking as an iterative, agent-driven process. Guided by an LLM, AutoLink dynamically explores and expands the linked schema subset, progressively identifying necessary schema components without inputting the full database schema. Our experiments demonstrate AutoLink's superior performance, achieving state-of-the-art strict schema linking recall of 97.4% on Bird-Dev and 91.2% on Spider-2.0-Lite, with competitive execution accuracy, i.e., 68.7% EX on Bird-Dev (better than CHESS) and 34.9% EX on Spider-2.0-Lite (ranking 2nd on the official leaderboard). Crucially, AutoLink exhibits exceptional scalability, maintaining high recall, efficient token consumption, and robust execution accuracy on large schemas (e.g., over 3,000 columns) where existing methods severely degrade-making it a highly scalable, high-recall schema-linking solution for industrial text-to-SQL systems.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 24 of its 32 references that are in the map. First posted on arXiv 21 Nov 2025.

Builds on

24 of 32 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2017Billion-scale similarity search with GPUscited by 2,497
  4. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  5. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  6. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  7. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 187
  8. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  9. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 164
  10. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 164
  11. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 138
  12. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 120
12 more
  1. 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
  2. 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 105
  3. 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learningcited by 68
  4. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  5. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
  6. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
  7. 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 52
  8. 2024A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQLcited by 46
  9. 2021SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQLcited by 43
  10. 2025LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQLcited by 29
  11. 2025Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Modelscited by 28
  12. 2022Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graphcited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 17.

17 papers.

Sort:

By area:

  1. 2026APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQLcited by 8
  2. 2026TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemascited by 3
  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. 2026Schema-First Retrieval: Embedding Catalogs for Natural Language Analyticscited by 1
  6. 2026MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQLcited by 1
  7. 2026IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Modelscited by 0
  8. 2026ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQLcited by 0
  9. 2026SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probingcited by 0
  10. 2026Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agentscited by 0
  11. 2026Database Context Compression for Text-to-SQL on Real-World Large Databasescited by 0
  12. 2026Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflowscited by 0
5 more
  1. 2026DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generationcited by 0
  2. 2026Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQLcited by 0
  3. 2026BudgetSchemaBench: A Budget-Swept Diagnostic for Schema Context in Text-to-SQLcited by 0
  4. 2026Enterprise Representation Simplification (ERS): Reducing Representational Complexity for Enterprise AIcited by 0
  5. 2026LYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinementcited by 0