arXiv · Information Retrieval· Shipei Lin, Duomin Zhang, Xiaolong Li, Bohan Hu, Bowen Qin, Jinyang Li, Chenhao Ma·· 4 hr agoAI score35
Diff-SQL：通过补丁生成与约束对齐优化 SQL 效率
Diff-SQL: SQL Efficiency Optimization via Patch Generation and Constraint Alignment
AI brief
Diff-SQL 是一个两阶段框架，将面向效率的优化与约束感知对齐解耦，先以统一 diff 补丁提出针对性修改，再用 on-policy 强化学习在可执行与语义等价约束下修正输出。
Source: arXiv · Information Retrieval · arxiv.org