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

新的自然语言到SQL基准和代理架构应对复杂企业数据

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-07 04:00

研究人员开发了一个新的基准和代理架构，用于处理复杂、嵌套的企业模式的自然语言到SQL系统。DevRev NL2SQL基准包含900个执行验证的查询和一个用于评估分析推理的语义深度得分（SDS）。提出的成本感知架构在此新基准上实现了91.7%的答案正确率，显著优于现有基线，并在Spider 2.0 Snowflake数据集上展示了具有竞争力的性能。 AI

影响这项研究可以改进企业使用自然语言查询复杂、嵌套数据的方式，从而可能简化数据分析和访问。

排序理由该集群包含一篇研究论文，详细介绍了新的基准和相关的自然语言到SQL任务系统。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 32 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇研究论文，详细介绍了新的基准和相关的自然语言到SQL任务系统。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Yoga Sri Varshan Varadharajan, Ajay Yadav, Ritesh Goru, Prateek Chaudhury, Constantine Caramanis, Prateek Jain, Divyateja Pasupuleti, Sunil Kumar Pandey · 2026-09-07 04:00

面向嵌套企业模式的自然语言到SQL的成本感知代理架构及新基准测试

arXiv:2609.04641v1 Announce Type: new 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 comp…

本文如何被排名

报道来源 [1]

面向嵌套企业模式的自然语言到SQL的成本感知代理架构及新基准测试

相关话题