针对企业级嵌套数据库，提出高效准确的自然语言转SQL框架。
A Cost-Aware Agentic Architecture for NL-to-SQL over Nested Enterprise Schemas, with a New Benchmark
- 设计成本感知的单次生成智能体架构，优化查询流程
- 在新基准上达91.7%正确率，领先第二名54.6个百分点
- 适合需要处理复杂嵌套数据库的企业级应用开发者
自然语言转SQL系统在学术基准上发展迅速，但实际企业级数据库呈现图结构、半结构化、深层嵌套的特点，现有基准无法有效衡量。本文提出两个互补贡献：一是构建DevRev NL2SQL基准，包含900个执行验证的查询，具有嵌套类型和链接图结构，并引入语义深度评分（SDS）作为不依赖模式的分析推理深度评估标准；二是提出一种成本感知的单次生成智能体架构，其模式选择、元数据检索与错误修复模块均针对该复杂场景设计。在DevRev NL2SQL基准上，系统达到91.7%的答案正确率，较次优基线高出54.6个百分点；在Spider 2.0 Snowflake公开数据集上，性能可与领先系统比肩，且保持单次生成运行方式。
原文摘要 · Abstract (English)
Natural-language-to-SQL systems have ad- vanced rapidly on academic benchmarks, yet production enterprise schemas exhibit graph- like, semi-structured, deeply nested structure that current benchmarks do not measure. We make two complementary contributions. First, we introduce the DevRev NL2SQL bench- mark: 900 execution-verified queries with nested-type and link-graph structure, accom- panied by the Semantic Depth Score (SDS), a schema-agnostic rubric for analytical reasoning depth. Second, we present a cost-aware single- generation agentic architecture whose schema- selection, metadata-retrieval, and error-repair components are designed for the requirements this regime imposes. On the DevRev NL2SQL benchmark the system attains 91.7% answer correctness, a margin of 54.6 percentage points over the next-best baseline; on the Spider 2.0 Snowflake public dataset, it is competitive with leading systems at a single-generation operating point.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。