mlsanityData to 14 Oct 2026

From Question-First to Analyst-First: Domain-Expert Skills and Verified Knowledge Compilation for Proactive Enterprise Analytics

arXiv 2608.28594 ↗First posted 15 Jun 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Conversational analytics systems assume the user already has a well-formed question, leaving a non-expert facing a blank query box on an unfamiliar enterprise schema. Commercial 'proactive' tools narrow this gap only by detecting statistical anomalies over analyst-curated metric layers, and academic next-question recommenders depend on query logs that a fresh dataset lacks. We describe a production analytics system that inverts the interaction model from question-first to analyst-first through two coupled architectural ideas. First, a pluggable domain-expert 'skill' abstraction: a folder-based, database-free subject-matter pack (a manifest, per-stage prompt facets, keyword-routed references, report templates, and optional compute) auto-selected per (client, dataset) by deterministic schema matching and spliced as a cross-cutting concern into every stage of an agentic pipeline, the schema explorer, and the report engines, degrading to a strict no-op when absent. Because a skill is a self-contained folder resolved deterministically, the catalogue is open-ended: an extensible marketplace of domain experts. Second, an offline knowledge-compilation loop: an agent probes the dataset's parquet via DuckDB (zero load on production), runs critic-gated per-table convergence with self-healing retries, and data-validates joins by value overlap, producing durable schema knowledge that drives standing expert reports whose every published metric is re-verified by re-executing its evidence SQL, plus suggested questions that mirror the report agenda. These close a proactive loop: reports surface numbers, the numbers seed questions, and a click launches a verified deep dive, all before the query box is used. We give a formal model and report illustrative single-tenant evidence. We make no user-study or benchmark claims; the contribution is the architecture and its defensibility.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 63 references that are in the map. First posted on arXiv 15 Jun 2026.

Builds on

35 of 63 references.

References · 35

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  7. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  8. 2023Let's Verify Step by Stepcited by 3,789
  9. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  10. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  11. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  12. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
23 more
  1. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  2. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  3. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  4. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  5. 2023Teaching Large Language Models to Self-Debugcited by 988
  6. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  7. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  8. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 232
  9. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 225
  10. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  11. 2024InfiAgent-DABench: Evaluating Agents on Data Analysis Taskscited by 140
  12. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 120
  13. 2024Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistancecited by 87
  14. 2023LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Modelscited by 82
  15. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  16. 2024Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLMcited by 35
  17. 2016Effortless Data Exploration with zenvisage: An Expressive and Interactive Visual Analytics Systemcited by 14
  18. 2025ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agentcited by 14
  19. 2018DataSite: Proactive Visual Data Exploration with Computation of Insight-based Recommendationscited by 12
  20. 2025Data-to-Dashboard: Multi-Agent LLM Framework for Insightful Visualization in Enterprise Analyticscited by 11
  21. 2017Foresight: Recommending Visual Insightscited by 10
  22. 2025A Scoping Review of Mixed Initiative Visual Analytics in the Automation Renaissancecited by 2
  23. 2024Automated Question Generation on Tabular Data for Conversational Data Explorationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026WinSyn: An Automated Pipeline for Realistic Enterprise Question-Answering Evaluation
  2. 2026Polaris : Multi Agentic System for Conversational Enterprise Analytics
  3. 2026A Multi-Agent Platform for Automated Enterprise Analytics and Insight Generation
  4. 2026Conversational Query Engine for Mixed-Modality Heterogeneous Enterprise Data Sources
  5. 2026Intent Graph: Navigating the Analytical Reasoning Space for Exploratory Data Analysis
  6. 2026DI-Bench: Systematically Generating In-Domain Data Intelligence Benchmarks for Enterprise Agents
  7. 2026Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
  8. 2026SEGRA: A Structured Experience Guided Reasoning Agent for Property Graph Question Answering