arXiv· Ibrahim Memon·· 5 天前精选AI 评分40
LuthorSQL 用 7B 本地模型先答数据库查询,API 成本降 33.3%
LuthorSQL: A One-Pass Text-to-SQL Model as System 1 for a Slower LLM Agent
AI 导读
Ibrahim Memon 在 arXiv 发表 LuthorSQL,一个非自回归 7B text-to-SQL 模型,作为慢速 LLM 智能体的快速前置层,只在不确定时升级给 Claude Opus 5.5。
变化判断
本地 7B 模型先答掉近一半数据库查询,API 调用减少三成,单次查询从调用托管模型变成一次前向计算。
正文 · 原文
Abstract:Frontier LLM agents that query databases with tools are among the most accurate text-to-SQL systems, but per-query calls to a hosted model are slow, costly, and expose sensitive organizational queries to external APIs. For example, a Claude Opus 5.5 agent serving 10,000 queries a day costs over $70,000 a year at list price. To what extent can local hardware already owned by an organization offload this burden without compromising the agent's accuracy? We present LuthorSQL, a non-autoregressive 7B text-to-SQL model that serves as a rapid System 1 gate for a slower LLM agent (System 2), escalating queries only when uncertain. LuthorSQL makes a single forward pass to predict slot scores over a bounded grammar for query plans, compiles and runs up to 32 candidate plans, and chooses an answer using a trained validator. On its own, LuthorSQL reaches 68.03% execution accuracy on BIRD's hidden test set at 0.84 s per question on a single GPU, maintains its accuracy in 9 GB with 8-bit quantized weights, and transfers zero-shot to Snowflake, BigQuery, MySQL, PostgreSQL, and DuckDB within 3.1 points of its native SQLite accuracy. Combined with Claude Opus 5.5 in a pre-registered confidence cascade over 227 questions on databases published after Opus's training cutoff, LuthorSQL answers nearly half of all questions locally and cuts API cost by 33.3% at the same accuracy. Finally, contamination probing shows that Opus reproduces 48-92% of public benchmark gold queries verbatim without seeing the schema; however, its tool-assisted accuracy holds on renamed schemas and reaches 95.6-97.4% on post-cutoff databases. Code and data: this https URL
| Comments: | 8-page main text plus appendix, 23 pages |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Databases (cs.DB); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.17780 [cs.CL] |
| (or arXiv:2611.17780v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.17780 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ibrahim Memon [view email]
[v1]
Fri, 13 Nov 2026 05:44:08 UTC (66 KB)
来源:arXiv · arxiv.org