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

arXiv: https://arxiv.org/abs/2610.06914 · HTML: https://mlsanity.com/paper/2610.06914/

## 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 (most cited first, 26 of 26)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021)
- [RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL](https://mlsanity.com/paper/2302.05965/) (2023)
- [Improving Text-to-SQL Evaluation Methodology](https://mlsanity.com/paper/1806.09029/) (2018)
- [MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization](https://mlsanity.com/paper/2402.11453/) (2024)
- [LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models](https://mlsanity.com/paper/2303.02927/) (2023)
- [NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queries](https://mlsanity.com/paper/2008.10723/) (2020)
- [Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness](https://mlsanity.com/paper/2301.08881/) (2023)
- [Data2Vis: Automatic Generation of Data Visualizations Using Sequence to Sequence Recurrent Neural Networks](https://mlsanity.com/paper/1804.03126/) (2018)
- [VisEval: A Benchmark for Data Visualization in the Era of Large Language Models](https://mlsanity.com/paper/2407.00981/) (2024)
- [DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing](https://mlsanity.com/paper/2401.10880/) (2024)
- [Data Formulator: AI-powered Concept-driven Visualization Authoring](https://mlsanity.com/paper/2309.10094/) (2023)
- [Data Formulator 2: Iterative Creation of Data Visualizations, with AI Transforming Data Along the Way](https://mlsanity.com/paper/2408.16119/) (2024)
- [SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution](https://mlsanity.com/paper/2608.05573/) (2026)

## 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.