TY - JOUR

T1 - Adapting the AI Scientist for Enterprise: Solving Real Business Problems with Autonomous Text-To-SQL Research

AU - Федоров, Вячеслав Васильевич

AU - Лавитская, Дарья Ивановна

AU - Ибрагимов , Д. М.

AU - Safronov, D.

AU - Баллес, А.

AU - Грибанова, А. Ю.

AU - Радионов, М. С.

N1 - Fedorov, V., Lavitskaya, D., Ibragimov, D. et al. Adapting the AI Scientist for Enterprise: Solving Real Business Problems with Autonomous Text-To-SQL Research. Dokl. Math. 112, 382–391 (2025).

PY - 2025/10

Y1 - 2025/10

N2 - One of the grand challenges in artificial intelligence is automating complex, multi-step reasoning tasks that require deep understanding of both natural language and structured data. While large language models have shown promise in code generation and natural language understanding, their ability to autonomously conduct end-to-end research in specialized domains remains limited. We ask a key question: can AI-driven research reliably solve real enterprise problems? This paper presents a fully automated framework for AI-driven research applied to the text-to-SQL problem, enabling frontier language models to independently generate novel ideas, design experiments, implement solutions, and communicate findings. We adapt the AI Scientist [1] – a comprehensive AI agent for autonomous scientific discovery – to the domain of semantic parsing, where it formulates hypotheses about improving text-to-SQL accuracy, writes executable code, runs experiments on benchmark datasets, visualizes performance gains, and produces complete scientific papers summarizing its results. Each full research cycle costs less than $5, making it a scalable and cost-effective approach for rapid innovation. This work moves toward self-improving AI systems in natural language processing, demonstrating robust performance across both proprietary and public benchmarks. Where AI agents not only solve tasks but also advance the state of the art by conducting independent research. Our code and generated papers are open-sourced at https://gitverse.ru/tr1ggers/AIScientist_Text2SQL.git.

AB - One of the grand challenges in artificial intelligence is automating complex, multi-step reasoning tasks that require deep understanding of both natural language and structured data. While large language models have shown promise in code generation and natural language understanding, their ability to autonomously conduct end-to-end research in specialized domains remains limited. We ask a key question: can AI-driven research reliably solve real enterprise problems? This paper presents a fully automated framework for AI-driven research applied to the text-to-SQL problem, enabling frontier language models to independently generate novel ideas, design experiments, implement solutions, and communicate findings. We adapt the AI Scientist [1] – a comprehensive AI agent for autonomous scientific discovery – to the domain of semantic parsing, where it formulates hypotheses about improving text-to-SQL accuracy, writes executable code, runs experiments on benchmark datasets, visualizes performance gains, and produces complete scientific papers summarizing its results. Each full research cycle costs less than $5, making it a scalable and cost-effective approach for rapid innovation. This work moves toward self-improving AI systems in natural language processing, demonstrating robust performance across both proprietary and public benchmarks. Where AI agents not only solve tasks but also advance the state of the art by conducting independent research. Our code and generated papers are open-sourced at https://gitverse.ru/tr1ggers/AIScientist_Text2SQL.git.

KW - semantic parsing

KW - large language models

KW - automated scientific discovery

KW - AI agent

KW - Text-to-SQL

KW - nl2sql

KW - database question answering

KW - autonomous research

KW - machine learning automation

KW - code generation

KW - self-improving AI

KW - program synthesis

UR - https://www.scopus.com/pages/publications/105033844918

U2 - 10.1134/S1064562425700474

DO - 10.1134/S1064562425700474

M3 - Article

VL - 112

SP - 382

EP - 391

JO - Doklady Mathematics

JF - Doklady Mathematics

SN - 1064-5624

IS - 2

ER -