研究测试时扩展的长期价值，发现记忆修复能显著提升文本转SQL准确率。
From Test-Time Scaling to Reusable Memory: Measuring Crystallization in Text-to-SQL
- 固定单次求解器，逐个测试不同记忆策略的效果。
- 在BIRD数据集上，记忆修复使首次尝试准确率提升4.34个百分点。
- 数据库特定内容是关键，可靠验证和广覆盖检索带来实际增益。
测试时扩展可纠正复杂的文本转SQL查询，但额外计算通常在得出答案后被丢弃。系统逐渐保留经验证的修复记录，但评估仍仅报告端到端得分，无法区分重复问题的重用与新问题的帮助，也难以定位有效记忆。我们称此为结晶化问题。通过控制实验，固定单次求解器并逐一改变记忆策略，分别测量重用、跨问题保留及同库未见数据迁移效果。在BIRD数据集上，存储经验证的修正查询使未见样本首次尝试准确率提升4.34个百分点，占按需修复提供准确率提升空间的44.4%。控制性干预表明，数据库特定内容是主要有效成分；可靠验证与更广检索范围带来增益，而更丰富格式或复杂检索器无效。代码、评估工具与复现说明已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。