This article walks through the design and implementation of a data‑analysis AI agent that converts natural‑language queries into SQL, executes them on a SQLite sales database, generates visualizations, and produces insight reports, complete with architecture diagrams and full Python code examples.
The paper defines the NLQ4TSDB problem of letting non‑expert users query massive time‑series data with natural language, builds the large‑scale NLQTSBench benchmark, proposes the neural‑symbolic Sonar‑TS framework that searches then verifies, and shows it outperforms existing baselines while highlighting remaining challenges.
It discusses Xiaomi DataAgent's third‑place ranking on the global BIRD Text‑to‑SQL benchmark, analyzes challenges such as model hallucination, lack of business knowledge, and complex multi‑table joins, and explains how a semantic harness addresses these problems to enable reliable enterprise data querying.
This article curates ten open‑source AI projects on Gitee that Java developers can use to learn RAG pipelines, AI agents, knowledge‑base construction, Text‑to‑SQL, workflow orchestration, and multi‑model integration, offering concrete use cases, learning goals, and guidance on selecting a learning path.
This article explains how to turn a simple Text‑to‑SQL demo into a production‑grade service by covering the underlying principles, layered architecture, risk‑control mechanisms, multi‑tenant security, high‑concurrency strategies, caching, observability, and deployment practices using Spring AI Alibaba.
QueryWeaver, an open‑source Text‑to‑SQL solution from FalkorDB, leverages a graph database to model schema relationships, offering instant natural‑language querying, MCP integration for AI IDEs, and a detailed comparison with Wren AI highlighting its fast, out‑of‑the‑box experience.
The article examines why single‑agent ChatBI solutions fall short in enterprise settings and presents a three‑layer, multi‑agent architecture—interaction, orchestration, and execution—built with Amazon Quick Suite, Amazon Bedrock AgentCore, and Snowflake Cortex AI, detailing routing, synchronous/asynchronous processing, semantic modeling, and deployment recommendations.
AutoLink introduces an autonomous, iterative schema‑linking approach for Text‑to‑SQL that treats schema discovery as a progressive, agent‑driven exploration, dramatically improving recall while cutting token costs, and outperforms existing database‑level and element‑level methods on large benchmarks such as Spider 2.0‑Lite and BIRD.
This article introduces the Agents‑Companion paradigm for Text‑to‑SQL, detailing how self‑describing database agents autonomously mine schema, statistics and semantics to generate high‑quality evidence, thereby bridging the gap between academic research and industrial deployment and significantly improving query accuracy.
This article details Ant Group’s DeepInsight intelligent evaluation system for Chinese Text‑to‑SQL, describing the AI‑BI background, challenges of existing benchmarks, a feature‑annotated evaluation design, automated dataset generation, experimental results showing a 46% accuracy gain and 71% reduction in failure rate, and future research directions.
The paper introduces DIVER, an automated expert system that gives large language models human‑like exploration, reasoning, and verification abilities for Text‑to‑SQL, addressing the severe performance drop without expert evidence by innovating dynamic interactive value linking, multi‑agent automation, and adaptive evidence generation, and demonstrates up to 10.82% accuracy gains and strong robustness on real‑world benchmarks.
AAAI 2026 accepted seven Xiaomi research papers—two oral presentations—covering multimodal sound editing, embodied 3D agent scheduling, scalable Text-to-SQL schema linking, parallel speculative decoding, long‑form speech QA, high‑level spatial navigation, and VLM‑driven autonomous‑driving adversaries, each with concrete datasets, methods, and benchmark gains.
BiomedSQL and LogicCat are two newly released Text‑to‑SQL datasets that challenge large language models with complex biomedical reasoning, multi‑step logical inference, and domain‑specific knowledge, offering detailed analyses of query types, scientific reasoning categories, and performance gaps that highlight current LLM limitations.
This article systematically presents Tencent PGC's Text‑to‑SQL research, detailing the DEA‑SQL framework, its agent‑based architecture, extensive experiments on benchmark datasets, and real‑world deployment in the OlaChat intelligent BI product, highlighting performance gains and practical capabilities.
Alibaba Cloud’s DB‑Surfer NL2SQL agent combines task‑planning, metadata linking, and a modular architecture to achieve state‑of‑the‑art performance on the Spider 2.0‑Snow benchmark and is now integrated into DataWorks Copilot, dramatically improving enterprise data query efficiency.
This article examines the evolution of Text-to-SQL, introduces the J‑Schema representation and chain-of-thought prompting, applies iterative DPO training and self-consistency voting, and demonstrates how these techniques raise execution accuracy on the BIRD benchmark from 56.6% to 69.2%.
This paper presents a comprehensive approach to improve Text‑to‑SQL performance by introducing J‑Schema for structured database representation, leveraging chain‑of‑thought prompting, applying iterative DPO training, and employing self‑consistency voting, achieving execution accuracy gains from 56.6% to 69.2% on the BIRD benchmark.
This article presents a comprehensive study on improving Text-to-SQL performance by introducing J‑Schema for structured schema representation, applying iterative Direct Preference Optimization (DPO) training, and leveraging self‑consistency voting mechanisms, achieving up to a 12% accuracy gain on the BIRD benchmark.
This article surveys the evolution of Text-to-SQL, introduces the J‑Schema representation and chain-of-thought prompting, details an iterative DPO training pipeline with hyper‑parameter tuning, and demonstrates how self‑consistency voting boosts execution accuracy on the BIRD benchmark from 56.6% to 69.2%.
At SIGMOD 2025 in Berlin, Alibaba Cloud presented its paper “OpenSearch‑SQL: Enhancing Text‑to‑SQL with Dynamic Few‑shot and Consistency Alignment,” which introduces a self‑taught few‑shot mechanism and multi‑agent alignment to significantly improve NL2SQL query accuracy, alongside a keynote on AI search trends.
With the rise of LLM‑based generative AI, this article examines the emerging GenBI (Generative Business Intelligence) paradigm, detailing why self‑serving analytics are needed, the progress of Text‑to‑SQL, an LLM‑driven agent architecture, practical AWS Bedrock implementation, technical choices, lessons learned, and future outlook.
This article provides a comprehensive overview of LLM-based Text-to-SQL technology, covering its background, evolution, challenges, various LLM-driven methods, benchmark datasets, evaluation metrics, and future research directions to guide researchers and practitioners in advancing natural language interfaces for databases.
The DIN‑SQL approach enhances Text‑to‑SQL performance by using large language models in a decomposed in‑context learning framework with schema linking, query classification, SQL generation, and self‑correction modules, achieving state‑of‑the‑art 85.3% execution accuracy on the Spider benchmark by breaking complex queries into manageable sub‑tasks.
This article explains how large language models can be used to convert natural language queries into SQL statements, describes two main approaches—direct generation and fine‑tuned open‑source models—details prompt engineering techniques, and outlines an end‑to‑end pipeline that executes the generated SQL and summarizes results.
This article reviews the Text-to-SQL semantic parsing task, covering its motivation, dataset landscape, major model architectures such as pointer networks, sequence‑to‑set, and grammar‑based approaches, evaluation metrics, the newly built DuSQL dataset and DuParser system, real‑world deployments, and remaining research challenges.
