SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL

Documenti analoghi

• Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search
  di: Li, Boyan, et al.
  Pubblicazione: (2025)
• TCSR-SQL: Towards Table Content-aware Text-to-SQL with Self-retrieval
  di: Xu, Wenbo, et al.
  Pubblicazione: (2024)
• Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL
  di: Pourreza, Mohammadreza, et al.
  Pubblicazione: (2025)
• Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward
  di: Weng, Han, et al.
  Pubblicazione: (2025)
• OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale
  di: Li, Haoyang, et al.
  Pubblicazione: (2025)