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

arXiv: https://arxiv.org/abs/2608.07213 · HTML: https://mlsanity.com/paper/2608.07213/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 66 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 30 of 30)

- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [CHESS: Contextual Harnessing for Efficient SQL Synthesis](https://mlsanity.com/paper/2405.16755/) (2024)
- [C3: Zero-shot Text-to-SQL with ChatGPT](https://mlsanity.com/paper/2307.07306/) (2023)
- [The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models](https://mlsanity.com/paper/2408.07702/) (2024)
- [RSL-SQL: Robust Schema Linking in Text-to-SQL Generation](https://mlsanity.com/paper/2411.00073/) (2024)
- [XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL](https://mlsanity.com/paper/2507.04701/) (2025)
- [Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL](https://mlsanity.com/paper/2505.20315/) (2025)
- [E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL](https://mlsanity.com/paper/2409.16751/) (2024)
- [DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework](https://mlsanity.com/paper/2510.17586/) (2025)
- [Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards](https://mlsanity.com/paper/2505.04671/) (2025)
- [AgentSM: Semantic Memory for Agentic Text-to-SQL](https://mlsanity.com/paper/2601.15709/) (2026)
- [Arming Data Agents with Tribal Knowledge](https://mlsanity.com/paper/2602.13521/) (2026)
- [Retrieval-Augmented LLM Agents: Learning to Learn from Experience](https://mlsanity.com/paper/2603.18272/) (2026)
- [Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents](https://mlsanity.com/paper/2605.17641/) (2026)
- [Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL](https://mlsanity.com/paper/2411.13244/) (2024)
- [Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs](https://mlsanity.com/paper/2602.02556/) (2026)
- [SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation](https://mlsanity.com/paper/2506.07423/) (2025)
- [RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System](https://mlsanity.com/paper/2508.17590/) (2025)
- [Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL](https://mlsanity.com/paper/2601.10011/) (2026)
- [Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents](https://mlsanity.com/paper/2606.00547/) (2026)
- [MemTrace: Probing What Final Accuracy Misses in Long-Term Memory](https://mlsanity.com/paper/2606.17328/) (2026)
- [RoboPhD: Self-Improving Text-to-SQL Through Autonomous Agent Evolution](https://mlsanity.com/paper/2601.01126/) (2026)
- [ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQL](https://mlsanity.com/paper/2511.00985/) (2025)
- [Continual Learning of Domain Knowledge from Human Feedback in Text-to-SQL](https://mlsanity.com/paper/2511.10674/) (2025)
- [EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement](https://mlsanity.com/paper/2605.00628/) (2026)
- [TAHOE: Text-to-SQL with Automated Hint Optimization from Experience](https://mlsanity.com/paper/2606.12387/) (2026)

## Abstract (arXiv)

Test-time scaling can correct difficult text-to-SQL queries, but the extra computation is normally discarded after each answer. Systems increasingly retain verified repair episodes, yet evaluations still report one end-to-end score. It cannot distinguish replay on recurring questions from help on unseen questions, or identify the responsible memory choice. We call measuring this future value the crystallization problem. Our controlled evaluation holds the single-shot solver fixed and varies one memory choice at a time. We separately measure replay, cross-question retention, and held-out same-database transfer. On BIRD, storing verified corrected queries improves held-out first-attempt accuracy by 4.34 percentage points. This gain captures 44.4% of the accuracy headroom provided by on-demand repair on the same questions. Controlled interventions identify database-specific content as the main operating ingredient. Reliable verification and broader retrieval coverage yield supported gains; richer formats and elaborate retrievers do not. Open-source code, evaluation artifacts, and reproduction instructions are available at https://github.com/ai-jiaqian/text-to-sql-memory-crystallization.