mlsanityData to 14 Oct 2026

SDAM: Structure-Difference-Aware Memory Evolution for Complex Text-to-SQL

arXiv 2608.12338 ↗First posted 3 Jun 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Text-to-SQL aims to convert natural language questions into executable SQL queries. While memory-based agent system improves complex SQL generation, existing memory design neglect historical experience and suffer from weak structure analysis, shallow semantic understanding, and poor schema alignment. To address these challenges, we propose SDAM. Specifically, SDAM identifies potential errors via a structure-difference aware reasoning tree, extracts deep semantic rules through contradiction-aware reflection, and enhances structural consistency using a schema-grounded memory evolution mechanism to bind memory with database schemas. We integrate SDAM into a Text-to-SQL framework named SDAM-SQL. Experiment shows that SDAM-SQL achieves 2.0 and 0.4 improvement on BIRD-dev and Spider-test compared with mainstream Text-to-SQL methods, showing the effectiveness of SDAM-SQL.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

21 of 32 references.

References · 21

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  2. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  3. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  4. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  5. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 398
  6. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  7. 2023FireAct: Toward Language Agent Fine-tuningcited by 256
  8. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  9. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 138
  10. 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Taskscited by 131
  11. 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 105
  12. 2023Agent Lumos: Unified and Modular Training for Open-Source Language Agentscited by 72
9 more
  1. 2023Exploring Chain-of-Thought Style Prompting for Text-to-SQLcited by 69
  2. 2024Online Adaptation of Language Models with a Memory of Amortized Contextscited by 35
  3. 2025Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Searchcited by 34
  4. 2023Divide and Prompt: Chain of Thought Prompting for Text-to-SQLcited by 20
  5. 2025Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Modelscited by 18
  6. 2024Archer: A Human-Labeled Text-to-SQL Dataset with Arithmetic, Commonsense and Hypothetical Reasoningcited by 13
  7. 2025Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuningcited by 13
  8. 2025Knowledge Base Construction for Knowledge-Augmented Text-to-SQLcited by 9
  9. 2025GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQLcited by 1

Built on by

Not cited yet.