cd /news/large-language-models/luthorsql-a-one-pass-text-to-sql-mod… · home › topics › large-language-models › article
[ARTICLE · art-170342] src=machinebrief.com ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

LuthorSQL: A One-Pass Text-to-SQL Model as System 1 for a Slower LLM Agent

A 7B non-autoregressive text-to-SQL model called LuthorSQL reaches 68.03% execution accuracy on BIRD's hidden test set at 0.84 seconds per question on a single GPU, according to an arXiv paper (2611.17780v1) from the model's authors. Used as a fast "System 1" gate ahead of a slower Claude Opus 5.5 agent 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, the authors report. The paper also finds that Opus reproduces 48-92% of public benchmark gold queries verbatim without seeing the schema, while its tool-assisted accuracy holds on renamed schemas and reaches 95.6-97.4% on post-cutoff databases.

by read1 min views1 publishedNov 16, 2026

arXiv:2611.17780v1 Announce Type: new 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: https://github.com/IAMIbrahimmemon/luthorsql

── more in #large-language-models 4 stories · sorted by recency
── more on @luthorsql 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/luthorsql-a-one-pass…] indexed:0 read:1min 2026-11-16 · —