mlsanityData to 14 Oct 2026

A Governed Agent Architecture for Natural-Language Dashboard Generation over Enterprise DataBrain

arXiv 2610.06914 ↗First posted 2 Oct 2026cs.AI cs.DBcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a DataBrain-specific prototype that turns natural-language analytic requests into inspectable dashboards. An installable Codex plugin and standalone Agent Runtime combine schema-constrained model decisions with typed tools, persistent state, and deterministic Hooks for approval, audit, checkpointing, recovery, and failure handling. The pipeline resolves entities, discovers metadata, enforces read-only SQL, composes dashboards, and applies static checks, dynamic preflight, and browser inspection. The model proposes actions while deterministic software controls execution and records state transitions. We evaluate the workflow on frozen real-DataBrain tasks and controlled Hook faults. Strict success was 6/8 on metadata and SQL tasks: metadata selection passed 4/4, all four SQL tasks met semantic criteria, and 2/4 met the exact output-column contract. The final release passed 4/4 single-panel dashboard tasks, one two-panel task, and one existing-dashboard refinement; a parameterised task exceeded its step limit. All ten fault scenarios met their specified outcomes without unapproved external side effects. Model inference accounted for over 97% of observed runtime in every reported group. These small, DataBrain-specific results do not establish production readiness, general text-to-SQL accuracy, or an efficiency advantage over manual dashboard construction.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 38 references that are in the map. First posted on arXiv 2 Oct 2026.

Builds on

26 of 38 references.

References · 26

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  3. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
  4. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
  5. 2023AgentBench: Evaluating LLMs as Agentscited by 1,267
  6. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  7. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  8. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 591
  9. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 548
  10. 2024InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agentscited by 538
  11. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  12. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
14 more
  1. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
  2. 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 268
  3. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
  4. 2018Improving Text-to-SQL Evaluation Methodologycited by 135
  5. 2024MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualizationcited by 102
  6. 2023LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Modelscited by 82
  7. 2020NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queriescited by 74
  8. 2023Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustnesscited by 53
  9. 2018Data2Vis: Automatic Generation of Data Visualizations Using Sequence to Sequence Recurrent Neural Networkscited by 48
  10. 2024VisEval: A Benchmark for Data Visualization in the Era of Large Language Modelscited by 45
  11. 2024DynaVis: Dynamically Synthesized UI Widgets for Visualization Editingcited by 37
  12. 2023Data Formulator: AI-powered Concept-driven Visualization Authoringcited by 32
  13. 2024Data Formulator 2: Iterative Creation of Data Visualizations, with AI Transforming Data Along the Waycited by 21
  14. 2026SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Executioncited by 1

Built on by

Not cited yet.