From Test-Time Scaling to Reusable Memory: Measuring Crystallization in Text-to-SQL

arXiv:2608.07213 · cs.CL · Submitted 2026-08-07 · Read on arXiv

Jiaqian Wang, Yutao Qi, Wenjin Hou, Yuanxi Che, Muning Wen

Xidian University · Xidian University · Xidian University · Xidian University · Shanghai Jiao Tong University

cs.CL

Submitted: 2026-08-07

Updated: 2026-08-10

Comments: 18 pages, 6 figures. Open-source code, evaluation artifacts, and reproduction instructions: https://github.com/ai-jiaqian/text-to-sql-memory-crystallization

Code: https://github.com/ai-jiaqian/text-to-sql-memory-crystallization

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Text-to-SQL — 54× in this paper · explained in 4 episodes
• Verification — 36× in this paper · explained in 2 episodes
• Accuracy — 22× in this paper · explained in 1 episode
• Benchmark — 15× in this paper · explained in 2 episodes
• Test-Time Scaling — 15× in this paper · explained in 4 episodes
• Trace — 11× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 8× in this paper
• Consistency — 7× in this paper · explained in 3 episodes
• Robustness — 6× in this paper · explained in 6 episodes
• Self-Consistency — 5× in this paper · explained in 3 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Association for Computational Linguistics — 3× in this paper
• Generalization — 3× in this paper · explained in 14 episodes
• Chain-of-Thought Prompting — 2× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• In-Context Learning — 2× in this paper · explained in 7 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 3 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Composition — 1× in this paper · explained in 2 episodes
• Continual Learning — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 1× in this paper
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generator — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 5 episodes
• Knowledge Base Construction — 1× in this paper · explained in 2 episodes
• Monotonicity — 1× in this paper · explained in 2 episodes
• Multi-agent Collaborative Framework — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 5 episodes
• Self-Evolving Agents — 1× in this paper · explained in 2 episodes
• Transactions on Machine Learning Research — 1× in this paper

Sources

• Arming Data Agents with Tribal Knowledge
• AgentSM: Semantic Memory for Agentic Text-to-SQL
• RoboPhD: Self-Improving Text-to-SQL Through Autonomous Agent Evolution
• E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL
• RSL-SQL: Robust Schema Linking in Text-to-SQL Generation
• RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System
• TAHOE: Text-to-SQL with Automated Hint Optimization from Experience
• Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL
• Continual Learning of Domain Knowledge from Human Feedback in Text-to-SQL
• C3: Zero-shot Text-to-SQL with ChatGPT
• Retrieval-Augmented LLM Agents: Learning to Learn from Experience
• XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL
• Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
• ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQL
• DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework
• Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
• MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
• The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models
• ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
• MemGPT: Towards LLMs as Operating Systems

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering