SQL-o1: Automatic Text-to-SQL Program Synthesis via Self-Reward Heuristic Search
cs.DB, cs.AI
Submitted: 2025-02-17
Updated: 2026-11-02
Code: https://github.com/ShuaiLyu0110/SQL-o1
Terminology
Sources
- GPT-4 Technical Report
- Dynamic Parallel Tree Search for Efficient LLM Reasoning
- C3: Zero-shot Text-to-SQL with ChatGPT
- Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
- A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL
- Mistral 7B
- Search-o1: Agentic Search-Enhanced Large Reasoning Models
- CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL
- ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
- CHESS: Contextual Harnessing for Efficient SQL Synthesis
- LLaMA: Open and Efficient Foundation Language Models
- Multi-Turn Interactions for Text-to-SQL with Large Language Models
- Qwen2.5 Technical Report
Related papers
- Beyond Overlap: Hierarchical Graph Abstraction for Out-of-Core Vector Search
- EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
- Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
- Samyama: A Unified Graph-Vector Database with In-Database Optimization, Agentic Enrichment, and Hardware Acceleration
- GenTUS: Table Union Search via Constrained Generation of Semantic Table Identifiers
- Common-Neighbor-Count-Based Representative Possible World Finding on Uncertain Graphs