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.
Abstract
Large language model agents are increasingly deployed for data-intensive work, yet reliable data analysis requires more than general-purpose reasoning and ad hoc tool augmentation. Data Agents, equipped with workflow harnesses, offer a promising paradigm for automating the end-to-end data science lifecycle. This paper examines Data Agents from a harness-centric perspective. First, we introduce a taxonomy of Data Agents and associated data environments, organizing the literature around five functional stages: perception, planning, execution, verification, and repair. Second, we analyze the key technical routes within each stage, identifying 15 distinct approaches ranging from data structure probing to data state reconstruction. Third, we identify four open reliability problems: inactive semantic calibration, missing clarification, missing experience transfer, and the missing verification-repair repository. These problems explain why silent failures can persist even when individual components function correctly, highlighting the need for rigorous workflow harnesses and shared reliability resources. Finally, we summarize the horizontal task families of Data Agents, examine their vertical application settings, and benchmarks for evaluation, while maintaining a companion repository at https://github.com/DEEP-PolyU/Awesome-Data-Agents.
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.
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.
Guo-Liang Li, Pei-Yao Zhou, Xuan-He Zhou et al.· IEEE Transactions on Knowled...· 0 citations
Results indicate that SciDSK improves how agents locate and understand scientific datasets, providing a stronger foundation for actionable scientific data use.
Xiao-Han Huang, Qing-Qing Long, Xiaolei Du 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.
MUSE is presented, an interactive meta-agent that enhances user understanding and control of agentic data science systems by dynamically restructuring low-level execution traces into multiple semantic levels that support navigation from high-level overviews to low-level implementation details.
Wei-Hao Chen, Weixi Tong, Yuan Tian et al.· 0 citations