大模型生成SQL易出错，这篇论文建模错误来精准修正，提高查询正确率。
arXiv:2603.03742v2 Announce Type: replace Abstract: Despite the remarkable performance of large language models (LLMs) in text-to-SQL (SQL generation)…
用知识图谱数据生成提升自然语言到Cypher查询精确度，为知识图谱问答提供新思路。
arXiv:2606.14325v1 Announce Type: cross Abstract: Property Graphs are rapidly being adopted as database frameworks for representing heterogeneous data…
揭密Text2SQL智能体如何探索关系数据系统，关键在于API调用需规范管控。
arXiv:2605.30862v1 Announce Type: cross Abstract: Text2SQL agents powered by LLMs translate natural language intent into SQL by exploring the data sys…
提出PQR框架自动生成多样真实用户查询，精准发现QA agent的失败边界，补足对抗性测试的盲区
arXiv:2605.16551v1 Announce Type: new Abstract: Evaluating LLM-based agents remains challenging because identifying meaningful failure cases often req…