{"slug": "luthorsql-a-one-pass-text-to-sql-model-as-system-1-for-a-slower-llm-agent", "title": "LuthorSQL: A One-Pass Text-to-SQL Model as System 1 for a Slower LLM Agent", "summary": "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.", "body_md": "arXiv:2611.17780v1 Announce Type: new \nAbstract: 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", "url": "https://wpnews.pro/news/luthorsql-a-one-pass-text-to-sql-model-as-system-1-for-a-slower-llm-agent", "canonical_source": "https://www.machinebrief.com/news/luthorsql-a-one-pass-text-to-sql-model-as-system-1-for-a-slo-ptsl", "published_at": "2026-11-16 05:00:00+00:00", "updated_at": "2026-11-16 05:25:11.868958+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "ai-research", "ai-tools", "natural-language-processing"], "entities": ["LuthorSQL", "Claude Opus 5.5", "BIRD", "Snowflake", "BigQuery", "MySQL", "PostgreSQL", "DuckDB"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/luthorsql-a-one-pass-text-to-sql-model-as-system-1-for-a-slower-llm-agent", "markdown": "https://wpnews.pro/news/luthorsql-a-one-pass-text-to-sql-model-as-system-1-for-a-slower-llm-agent.md", "text": "https://wpnews.pro/news/luthorsql-a-one-pass-text-to-sql-model-as-system-1-for-a-slower-llm-agent.txt", "jsonld": "https://wpnews.pro/news/luthorsql-a-one-pass-text-to-sql-model-as-system-1-for-a-slower-llm-agent.jsonld"}}