QwenPaw-Data: Bridging Facts, Methodology, and Execution for Autonomous Enterprise Data Analytics

2026-07-12

AI Summary

This work addresses the challenges posed by enterprise data environments—characterized by openness, ambiguity, and continuous evolution—that hinder traditional analytical approaches from supporting reliable, traceable, and self-evolving intelligent analysis. To overcome these limitations, the paper proposes an autonomous agent system for enterprise intelligent data analytics, featuring an integrated asset flywheel architecture that unifies semantics, methodology, execution, and evolution. This architecture automatically translates natural language requests into end-to-end analytical workflows. The system comprises three synergistic subsystems: DataBridge (a metadata–knowledge–trajectory graph), Skill-Hub (which codifies expert methods as reusable skills), and Host (a centralized artifact runtime). Together, they enable analytical assets to be reusable, governable, and self-evolving. Experiments demonstrate that the system significantly enhances verifiable data access and high-level analytical quality on both public benchmarks and real-world industrial BI workloads, establishing a practical foundation for trustworthy enterprise data agents.

Abstract

Enterprise data analysis is emerging as a distinct frontier for autonomous agents. Compared with general-purpose interaction and software engineering, it operates in an open, ambiguous, and continuously evolving environment. These characteristics call for a data-agent architecture that treats semantics, methodology, execution, and evolution as first-class system concerns. To this end, we introduce QwenPaw-Data, an agentic data system designed for enterprise intelligent data analysis. QwenPaw-Data consolidates heterogeneous assets from warehouses, dashboards, documents, interaction logs, and historical tasks into reusable, governable, and evolvable analysis assets, then turns natural-language requests into end-to-end analytical workflows spanning data understanding, retrieval, analysis, report generation, and decision support. Its architecture decomposes the problem into three collaborative subsystems: DataBridge provides trustworthy semantic grounding through interconnected metadata, knowledge, and trace graphs; Skill-Hub codifies expert analytical methodology into reusable and verifiable skills; and Host materializes these evidence and method assets into controllable, artifact-centric runtime execution. Across these subsystems, semantics, methods, traces, and feedback are continuously deposited back into the system, forming a self-evolving asset flywheel. Experiments on public benchmarks and real-world industrial BI workloads show that QwenPaw-Data improves both verifiable data access capability and higher-level analytical quality, offering a practical foundation for reliable, traceable, and continuously improving enterprise data agents.

Problem

• autonomous data analysis
• enterprise data analytics
• semantic grounding
• methodology codification
• self-evolving systems

Innovation

• autonomous data agents
• semantic grounding
• reusable analytical skills
• self-evolving system
• enterprise data analytics