A Cost-Aware Agentic Architecture for NL-to-SQL over Nested Enterprise Schemas, with a New Benchmark

2026-09-03

AI Summary

本文针对企业级复杂模式下的自然语言转SQL问题，提出了一种成本感知的代理架构及新的基准测试DevRev NL2SQL。

Abstract

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.

Problem

• Natural-language-to-SQL
• Enterprise Schemas
• Nested Structure

Innovation

• cost-aware agentic architecture
• nested enterprise schemas
• DevRev NL2SQL benchmark
• Semantic Depth Score (SDS)