mlsanityData to 7 Oct 2026

Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents

arXiv 2606.19319 ↗First posted 17 Jun 2026cs.MA cs.AI cs.DBcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Production data integration is bottlenecked by repeated, lossy handoffs between data owners, engineers, and analysts who must collaboratively discover, structure, and query enterprise data. We present Data Intelligence Agents (DIA), a system of three agents (Data Interpreter, Schema Creator, and Query Generator) that compresses this workflow by treating autonomous coding agents (ACAs) as a first-class abstraction: rather than emitting text, the agents generate, execute, validate, and repair concrete artifacts, draw on a shared memory for experience reuse, and surface each for review by domain experts. DIA is deployed in production for enterprise customers. We study the Query Generator in depth and evaluate it in fully autonomous mode across seven SQL benchmarks spanning four task categories and four dialects. It matches or surpasses the best published results on all seven, demonstrating that an architecture grounded in execution, built on ACAs and a shared memory, generalizes across the data intelligence workload with adaptation confined to natural-language instructions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 34 of its 41 references that are in the map. First posted on arXiv 17 Jun 2026.

Builds on

34 of 41 references.

Closest ancestors · 9

Same direction, newest first

  1. 2026AgentNLQ: A General-Purpose Agent for Natural Language to SQL18 May
  2. 2026APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL11 Feb
  3. 2026AgentSM: Semantic Memory for Agentic Text-to-SQL22 Jan
  4. 2025DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle3 Dec
  5. 2025MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL2 Nov
  6. 2025RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System25 Aug
  7. 2025Coding Agents with Multimodal Browsing are Generalist Problem Solvers3 Jun
  8. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration2 Feb
  9. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL18 Dec

Other references · 25

  1. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  2. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
  3. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  4. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  5. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 180
  6. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  7. 2019SParC: Cross-Domain Semantic Parsing in Contextcited by 141
  8. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  9. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  10. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 90
  11. 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 51
  12. 2024A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQLcited by 46
13 more
  1. 2024Understanding the Effects of Noise in Text-to-SQL: An Examination of the BIRD-Bench Benchmarkcited by 33
  2. 2025Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scalingcited by 20
  3. 2025BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactionscited by 17
  4. 2025AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scalecited by 15
  5. 2025Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidancecited by 14
  6. 2025Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generationcited by 8
  7. 2024Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQLcited by 5
  8. 2026NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agentscited by 5
  9. 2026Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agentscited by 4
  10. 2026Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQLcited by 3
  11. 2026DeepPrep: An LLM-Powered Agentic System for Autonomous Data Preparationcited by 3
  12. 2025Text2Schema: Filling the Gap in Designing Database Table Structures based on Natural Languagecited by 2
  13. 2025Declarative Techniques for NL Queries over Heterogeneous Datacited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness
  2. 2026Data Agents: Agentic Data Systems
  3. 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
  4. 2025LLM and Agent-Driven Data Analysis: A Systematic Approach for Enterprise Applications and System-level Deployment
  5. 2026Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses
  6. 2026QwenPaw-Data: Bridging Facts, Methodology, and Execution for Autonomous Enterprise Data Analytics
  7. 2026A Cost-Aware Agentic Architecture for NL-to-SQL over Nested Enterprise Schemas, with a New Benchmark
  8. 2025Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems