SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning
英文标题：SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning
arXiv:2608.00485v1 Announce Type: new Abstract: Recent Text-to-SQL systems increasingly rely on multi-turn interaction, execution feedback, and reinforcement learning. However, most existing methods use execution correctness only as a trajectory-level reward, which provides limited guidance for ide
打开原文相关 2.4 · 机会 1
2.6 KB
2.1 KB
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2608.00485v1 Announce Type: new Abstract: Recent Text-to-SQL systems increasingly rely on multi-turn interaction, execution feedback, and reinforcement learning. However, most existing methods use execution correctness only as a trajectory-level reward, which provides limited guidance for ide
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×