Tagged articles
Text-to-SQL
48 articles · Page 1 of 1
Google Cloud's Knowledge Catalog now integrates six semantic modeling systems — LookML, dbt MetricFlow, Snowflake Semantic Views, Databricks Metric Views, BigQuery Graph, and SAP CSN — into a unified Context Graph, letting enterprise Data Agents retrieve verified business definitions instead of inferring them from raw schemas, improving query accuracy nearly 4× while cutting token usage up to 75%.
Context GraphData AgentsGoogle Cloud
0 likes · 25 min read

This article analyzes Tencent's DataBuddy architecture to show how a business semantic layer — combining ontology and semantic models — enables reliable enterprise Data Agents by resolving metric ambiguity, ensuring consistent definitions, and compiling semantic SQL to physical SQL, moving beyond error-prone NL2SQL demos to production-grade analytics.
AI agentBusiness IntelligenceData Agent
0 likes · 22 min read

AsiaInfo's telecom case study shows a four-stage ontology-driven pipeline — task understanding, knowledge location, relationship completion, and layered workset delivery — achieves 98.6% object recall, 4.2s retrieval, and 83.5% SQL first-pass rate on 150 real queries, proving task-oriented knowledge organization as a core agent capability.
AI agentsAsiaInfoGraphRAG
0 likes · 22 min read

This article details a production-grade SQL generation engine using a semantic layer, NL2DSL via RAG, and deterministic DSL2SQL translation, achieving 85-90% accuracy through ambiguity detection, validation, permission injection, and feedback loops.
DSL2SQLData EngineeringLLM
0 likes · 15 min read

Xiaomi details its production Data Agent architecture — multi-level semantic fallback, multi-path SQL generation with voting, data lineage traceability, automated evaluation loops, and anti-decay monitoring — achieving 90%+ accuracy across finance, HR, and billing scenarios with 10x efficiency gains.
BIRD BenchmarkData AgentEvaluation Harness
0 likes · 19 min read

This article details a comprehensive governance framework for deploying Text-to-SQL systems in production, covering threat modeling, AST validation, multi-tenant isolation, performance admission via EXPLAIN, database permission hardening, budget-aware execution, cancellation semantics, and phased rollout strategies to ensure secure, auditable, and revocable data access.
AST ValidationEXPLAIN PlanJSqlParser
0 likes · 39 min read

This article analyzes ontology-enhanced NL2SQL systems, showing that their true value lies in forcing enterprises to explicitize and govern business semantics—metrics, dimensions, rules—rather than merely improving SQL accuracy, detailing modeling components, construction pipelines, online execution architectures, and the shift toward ontology-as-tool-interface.
LLMNL2SQLSemantic Layer
0 likes · 29 min read

This article presents a comprehensive engineering framework for production Text-to-SQL systems, covering schema contracts, prompt engineering, retrieval with permission-aware evidence closure, multi-layer SQL validation, execution isolation, and evaluation methodologies centered on business correctness and security boundaries.
LLM ApplicationsSQL GenerationSchema Management
0 likes · 43 min read

The article presents a complete engineering framework for production Text-to-SQL systems, covering semantic contracts, metadata retrieval, controlled query compilation, security enforcement, execution budgets, evaluation, and phased rollout, using a "East China weekly payment GMV YoY" case study to demonstrate how to deliver trustworthy, auditable analytical answers rather than just executable SQL.
Execution BudgetMetadata RetrievalProduction Engineering
0 likes · 45 min read

The article compares three technical approaches for natural language data querying—Text-to-SQL, Text-to-DSL, and Data Agent—analyzing their principles, strengths, limitations, and enterprise selection criteria, while emphasizing semantic layers, multi-step analysis, and phased implementation.
Business IntelligenceData AgentSemantic Layer
0 likes · 18 min read

Amap shares four conference talks detailing how they built trustworthy AI agents for business decisions, covering semantic governance, causal evaluation, evaluation-driven development, and a product architecture shift that lifted accuracy from 50% to 95% by separating deterministic computation from model reasoning.
AI agentsAmapBusiness Analytics
0 likes · 21 min read

In an 80-minute interview, Turing Award winner Mike Stonebraker argues that relational databases will absorb AI workloads, explains why Text-to-SQL fails on real enterprise data due to schema corruption and access controls, details DBOS's persistent workflow approach for AI agents, and discusses saga patterns for compensating transactions, graph database limitations, and the future of open-source AI.
AI agentsDBOSGraph Databases
0 likes · 27 min read

Amap's intelligent query product raised accuracy from 50% to 95% by replacing RAG with a Skill-based Agent architecture that uses on-demand knowledge retrieval and self-reflection, backed by semantic layer modeling and a three-part evaluation flywheel.
Agent ArchitectureAmapBI
0 likes · 6 min read

The article explains why directly using LLMs to generate SQL leads to sub-50% accuracy in production, and presents a proven three-layer architecture—semantic layer for business knowledge, LLM layer for structured DSL generation, and deterministic execution layer for dialect-specific SQL translation—that achieves 85-90% accuracy through RAG, ambiguity detection, and feedback loops.
DSLDatabase DialectsLLM
0 likes · 15 min read

The article argues that most enterprise AI agents don't need to traverse graph databases; instead, they need curated context (definitions, join keys, governance rules) to write SQL directly. It distinguishes Lookup questions (known paths) from Path questions (where the path is the answer), showing that Lookup dominates and graph traversal adds latency and cost without benefit.
AI agentsGraph DatabasesGraphRAG
0 likes · 20 min read

This article explains why syntactically correct AI-generated SQL often fails to reflect business logic, introduces StarRocks' Semantic View as an executable 'information contract' that defines metrics, relationships, and synonyms, and demonstrates with a fishing gear example how it enables deterministic SQL expansion for both AI agents and BI tools.
AI-generated SQLBusiness LogicData Modeling
0 likes · 15 min read

SQLBot is an open-source ChatBI tool that uses LLMs and RAG to convert natural language questions into SQL queries, generate visualizations, and provide AI-driven insights, enabling non-technical users to perform data analysis without writing code.
ChatBIDockerLLM
0 likes · 6 min read

This article argues that enterprise Data Agents require a seven-layer data architecture—source, preparation, object, semantic, permission, execution, and verification—rather than simply connecting databases to LLMs, detailing how each layer resolves ambiguity, ensures stability, enforces security, and enables trustworthy analytical reasoning.
AI analyticsBusiness IntelligenceData Agent
0 likes · 18 min read

The article explains that NL2SQL translates natural language into SQL queries, offering a narrow but reliable form of data‑centric programming, while highlighting its boundaries, recent multi‑step extensions, and its role within broader natural‑language‑to‑code ecosystems.
AI programmingNL2SQLText-to-SQL
0 likes · 8 min read

Large language models generate SQL by predicting tokens rather than truly understanding databases, leading to four categories of hallucinations—factual, logical, instructional, and knowledge‑boundary—each with concrete examples, and the article outlines five practical strategies such as schema‑pre‑alignment, execute‑then‑rerank, compiler feedback, real‑time schema sync, and human verification to curb these errors.
AI HallucinationRAGSQL validation
0 likes · 9 min read

The article traces four generations of enterprise data intelligence—from BI dashboards to Text‑to‑SQL and finally Data Agents—explaining why successful deployment depends on five engineering disciplines (Context, Knowledge, Skill, Memory, Evaluation Loop) rather than the underlying LLM model.
Data AgentEnterprise Data IntelligenceEvaluation Loop
0 likes · 18 min read


21CTOJul 20, 2026 · Databases
In a candid interview, database pioneer Mike Stonebraker recounts the academic and commercial journeys of Ingres and Postgres, critiques industry giants, explores his DebOS project that reimagines OS kernels as databases, and shares hard‑won insights on AI‑driven Text‑to‑SQL and career advice for the next generation.
AIDebOSIngres
0 likes · 11 min read

In a candid interview, PostgreSQL founder Michael Stonebraker recounts his journey from Ingres to Postgres, critiques Oracle’s sales tactics, denounces Google’s and Amazon’s database strategies, explains Postgres’s extensible type system, explores the DBOS research project, and highlights why current large‑language‑model‑to‑SQL solutions remain far from production‑ready.
AIDBOSDatabase Architecture
0 likes · 25 min read

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.
AI agentLLMLangChain
0 likes · 9 min read

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.
NLQ4TSDBSonar-TSText-to-SQL
0 likes · 9 min read

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.
BIRD BenchmarkDataAgentLLM
0 likes · 13 min read

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.
AIJavaLangChain4j
0 likes · 13 min read

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.
SecuritySpring AIText-to-SQL
0 likes · 40 min read

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.
AI IDEMCPOpenAI
0 likes · 13 min read

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.
Amazon Bedrock AgentCoreAmazon Quick SuiteMulti-Agent Architecture
0 likes · 15 min read

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.
AgentAutoLinkDatabase exploration
0 likes · 19 min read


Amap TechJan 28, 2026 · Artificial Intelligence
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.
AIAgentsDatabase Mining
0 likes · 8 min read

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.
AIText-to-SQLbenchmark
0 likes · 13 min read

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.
Automated Expert AgentChatBIDIVER
0 likes · 11 min read

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.
AAAI 2026Autonomous DrivingEmbodied AI
0 likes · 13 min read

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.
BiomedicalDatasetLLM
0 likes · 9 min read

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.
Agent ArchitectureDEA-SQLText-to-SQL
0 likes · 20 min read

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.
Agentic AIDataWorksNL2SQL
0 likes · 7 min read


JD TechAug 20, 2025 · Artificial Intelligence
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%.
BIRD BenchmarkIterative DPOJ-Schema
0 likes · 11 min read

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.
BIRD BenchmarkIterative DPOSelf-Consistency
0 likes · 12 min read

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.
Database QAIterative DPOJ-Schema
0 likes · 10 min read

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%.
BIRD datasetIterative DPOLLM
0 likes · 14 min read

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.
Database AIFew-Shot LearningNL2SQL
0 likes · 5 min read

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.
AWS BedrockAgentic AIBusiness Intelligence
0 likes · 18 min read

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.
LLMText-to-SQLdatabase
0 likes · 18 min read

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.
AI researchDatabase QueryingNLP
0 likes · 34 min read

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.
ChatGLMLLMSQL Generation
0 likes · 7 min read

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.
AIText-to-SQLdatabase
0 likes · 20 min read
