Sep 2026· IEEE Transactions on Knowledge and Data Engineering· 0 citations· 66 references
Computer Science
TL;DR
This work proposes a new paradigm called the Data Agent, designed to manage, process, and analyze data with minimal human intervention, and develops two specialized agents: the data analytics agent and the data science agent.
Abstract
Traditional data systems face profound limitations in the AI era, relying on human-crafted pipelines, lacking semantic understanding of heterogeneous data, and operating through rigid, reactive processing. To address these challenges, we propose a new paradigm called the Data Agent, designed to manage, process, and analyze data with minimal human intervention. Data agents autonomously execute a wide range of data-related tasks, transforming traditional data systems by shifting from manual design to autonomous orchestration, from literal manipulation to semantic interpretation, and from reactive to proactive processing. Our Data Agent system includes six components: semantic data organization, semantic operators, agentic pipeline orchestration and optimization, feedback-driven refinement, memory management, and proactive adaptation. Building on this foundation, we also develop two specialized agents: the data analytics agent and the data science agent. Experiments on real benchmarks demonstrate significant performance gains of our data agent over state-of-the-art methods. We identify open challenges to guide future research in building fully autonomous data systems.
This paper examines Data Agents from a harness-centric perspective, introducing a taxonomy of Data Agents and associated data environments, and identifying four open reliability problems: inactive semantic calibration, missing clarification, missing experience transfer, and the missing verification-repair repository.
Hua-Chi Zhou, Yu-Jing Zhang, Jia-He Du et al.· 0 citations
The AgenticData system, an agentic data system that enables natural-language query analytics over heterogeneous data sources, is introduced and its ability to handle diverse data sources accurately and efficiently is illustrated.
Pei-Yao Zhou, Ji Sun, Yao-Qiang Xu et al.· 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.
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.
Comparisons against stronger model and coding-agent competitors further indicate that both domain-specific agent runtime structure and foundation-model strength matter for autonomous data analysis.
Cognitive-inspired DataOps is presented as a conceptual framework for an autonomous data pipeline that provides a structured framework for advancing DataOps from reactive workflow automation to more autonomous, resilient and explainable operations, while also paving the way for research into reasoning-driven orchestrat...
Aymen Fannouch, Jihane Gharib, Youssef Gahi· EPJ Web of Conferences· 0 citations
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.