A data engineering analysis argues that reliable enterprise text-to-SQL depends less on model choice than on the context built around the model, citing production write-ups from Uber and LinkedIn and …
A controlled evaluation of eight generated LLM harnesses plus a baseline and nine byte-identical baseline copies on 386 MATH-500 tasks found that identical programs alone yield 2.16 percentage points …
A framework called IESR (Information Enhanced Structured Reasoning) achieved state-of-the-art results on the complex reasoning benchmark LogicCat with 24.28 EX and on the Archer dataset with 37.28 EX …
COAL-SQL, a unified post-training framework combining Coverage-Guided Augmentation (CGA) and Failure-Driven Learning (FDL), achieves 64.9% execution accuracy on the BIRD development set using only 12,…
A fine-tuned model called ReViSQL-K2.6, developed by Tinker using reinforcement learning with verifiable rewards, exceeds the human benchmark of 92.96% on the BIRD text-to-SQL task, reaching 92.96% wh…
Researchers propose TraceSQL, a lightweight verification model that uses 67 explicit diagnostic features to estimate whether generated SQL correctly answers a user question without ground-truth refere…
Motley AI's open-source semantic layer SLayer improved text-to-SQL accuracy by over 34% on production-scale databases, with the SLayer agent passing 153 of 265 tasks (57.7%) versus 114 (43.0%) for a r…
BAP-SQL, a budget-aware observation planning method for agentic text-to-SQL, improves tight-budget success by 3.4/3.6 percentage points over matched SFT on the BIRD-derived setting while using 4.5/5.0…
Anthropic measured that without skills, Claude's ability to answer analytics questions accurately didn't exceed 21% on their evals, but with a structured stack including governed datasets and semantic…
AutoThinkSQL, a framework integrating an auto-thinking mechanism into Supervised Fine-Tuning and Direct Preference Optimization for Text-to-SQL, enables dynamic bypassing of reasoning for simple queri…
Researchers propose BIRD (Bootstrapped Iterative Self-Reasoning Distillation), a two-stage method that improves compressed reasoning by first generating concise, correct traces from a base model under…
Feyn AI, a YC-backed startup, released SQRL, a family of text-to-SQL models that inspect the database before writing a query. The flagship SQRL-35B-A3B achieves 70.6% execution accuracy on BIRD Dev, o…
Sqlsure, a deterministic semantic checker for AI-generated SQL, catches logical errors like double-counted revenue and exposed patient identifiers that databases and linters miss. The tool, which runs…
A study on text-to-SQL systems found that verification-based signals, such as LLM judges, outperform black-box signals like self-consistency in predicting query correctness, with a two-provider ensemb…
Researchers introduced Outcome Reward Models (ORMs) for Text-to-SQL verification, using semantic scoring to outperform traditional heuristics. Their GradeSQL framework automates candidate generation a…
Researchers introduced GradeSQL, a framework for training Outcome Reward Models (ORMs) to improve test-time verification in Text-to-SQL tasks. ORM-based selection outperformed execution-based Best-of-…
Google Research's Gemini-SQL2, built on Gemini 3.1 Pro, achieved 80.04 percent accuracy on the BIRD text-to-SQL benchmark, surpassing OpenAI and Anthropic. The technology aims to enhance natural langu…
Google Research announced Gemini-SQL2, a text-to-SQL capability powered by Gemini 3.1 Pro, which achieved 80.04% execution accuracy on the BIRD Single-Model Leaderboard, surpassing its predecessor Gem…
Researchers introduced EnterpriseMem-Bench, a multi-turn Text-to-SQL benchmark of 300 sessions and 1,400 queries built from three enterprise domains, to evaluate how five frontier AI models handle mem…