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.
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.
DataClawEval is introduced, the first comprehensive benchmark designed specifically to evaluate the end-to-end task completion capabilities of autonomous agents in real-world data engineering scenarios, and it comprises 100 rigorous, end-to-end tasks spanning five execution engines.
Debin Meng, Jiaming Yang, Zefang Zong et al.· 0 citations
DataSpace, a benchmark in which data agents produce verifiable tabular results from task-local heterogeneous workspaces, is introduced and key challenges for improving data-agent reliability are identified.
Boyan Li, Zhuowen Liang, Yupeng Xie et al.· 1 citation
Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coordinated use of tools such as notebooks, IDEs, terminals, browsers, and databases within real operating environments. Yet existing benchmarks lack real-computer interaction and do not evaluate whether agents can execute complete end-to-end data-science workflows in realistic computing environments, failing to capture the multi-stage, multi-tool nature of data-science practice. We introduce DSAgentBench, the first benchmark to evaluate whether agents can automate full data-science workflows inside real computer environments. DSAgentBench contains 275 diverse tasks covering the entire data-science life-cycle, reflecting the complexity and tool coordination required in practice. Each task requires grounding decisions in intermediate outputs and coordinated tool use, and includes a deterministic evaluator that verifies analytical correctness, visual outputs, and model performance rather than code-only execution. Our extensive experiments with 15 closed- and open-source models show that even the strongest agent, Claude-4.6-Sonnet, achieves only 56.70% task success, while all open-source agents remain below 1%, frequently failing at tool orchestration, OS grounding, and multi-step reasoning. These results reveal a substantial capability gap between current agentic systems and real data-science workflows, positioning DSAgentBench as a foundation for developing grounded, verifiable, autonomous data-science agents. We release DSAgentBench at https://github.com/vis-nlp/DSAgentBench.
Mizanur Rahman, Mohammed Saidul Islam, Ridwan Mahbub et al.· 0 citations
The findings advocate for the integration of AI-powered pipelines within ERP systems as a transformative approach to enable scalable, intelligent, and high-fidelity data processing, essential for next- generation enterprise software resilience and performance.
Yuvaraj Kavala· International Journal of Com...· 0 citations
This work presents DeepEye, a workflow-centric agentic data system that turns user intents into transparent and steerable analytical workflows and develops DataMagic as the system’s Video Generator, a declarative multi-agent method that improves data-video quality.
Cognitive Data Engineering (CDE) is an advanced paradigm that integrates artificial intelligence, machine learning, and knowledge-based systems into traditional data engineering to enable automated and intelligent data management. This paper presents a Cognitive Data Engineering Framework (CDEF) designed to automate key data lifecycle processes such as ingestion, transformation, integration, quality assurance, and governance. Unlike conventional rule-based pipelines, the proposed framework adapts dynamically to data changes, anomalies, and schema evolution through self-learning and context-aware capabilities. The framework employs metadata-driven intelligence, semantic modeling, reinforcement learning, and cognitive agents within a layered architecture comprising perception, reasoning, learning, and execution. It also leverages knowledge graphs and ontologies to enhance semantic interoperability and data discovery. Experimental results demonstrate improved performance, reduced errors, and increased flexibility compared to traditional systems. Overall, the study highlights the potential of CDEFs in enabling efficient, scalable, and autonomous data management, with future scope in edge computing, real-time analytics, and self-governing data ecosystems.
Fatima Noor, Suresh Babu Reddy· International Journal of Dat...· 0 citations