The benefits of TexeraAgent are shown, including how an analyst easily understands the agent’s behaviors through an intuitive dataflow-based interface, how the analyst efficiently inspects the agent’s past actions to provide feedback, and how the agent can finish a task with high accuracy and low cost.
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
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.
In today's fast-paced environment, the ability to swiftly access, understand, and act on data is no longer optional; it is essential. Yet most organizations remain data-rich but insight-poor, constrained by the complexity of querying, interpreting, and explaining enterprise-scale information. We present Polaris, a supervisor-led multi-agent framework for conversational enterprise analytics that bridges this gap. Polaris introduces Dynamic Task Coordination (DTC), a decision-theoretic orchestration layer that models agent-task assignment as adaptive bipartite matching, enabling real-time coordination, recovery, and optimization across specialized agents for querying, visualization, and reasoning. By coupling DTC with reason-first, ReAct-style agents, Polaris transforms natural-language queries into coherent analytical workflows that not only retrieve and visualize data but also explain the underlying"why."Evaluation on structured enterprise datasets demonstrates high semantic fidelity and answer relevancy, underscoring the potential of multi-agent orchestration to deliver trustworthy, end-to-end business intelligence at scale.
K. VaruniH., Soham Sarkar, J. Kumar et al.· 0 citations
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.
Summary Agentic AI platforms enable the engineering of autonomous workflows but are not designed for experimentation and hypothesis testing. ASAREE (Analytical Sandbox for Agentic AI Research, Engineering, and Experimentation), is an open-source platform to address this gap. ASAREE creates agents, connects to MCP servers and tools, and designs factorial experiments through a visual interface or Python SDK. It records a full provenance trace for every run and routes all model calls through a provider-agnostic bridge that supports local deployments, ensuring data privacy. As a use-case, we use ASAREE to evaluate key design choices in a mutli-agent machine learning pipeline. Across a 2 × 2 × 2 factorial design, more advanced models, greater reasoning effort, and critic agent use significantly increased compute time, token use, cost, and feature count without improving predictive performance. The lowest-cost baseline, Claude Sonnet 5 with medium effort and no critic, achieved the highest mean PR AUC while Claude Opus 5 with extra high effort and a critic agent cost 15.5× more (USD) and ran 13.1× longer while performing worse on average. These findings highlight ASAREE as a robust framework for evaluating agentic system performance and resource efficiency. Availability and implementation ASAREE is available on GitHub at: https://github.com/EpistasisLab/ASAREE. Contact jason.moore@csmc.edu Supplementary Information Supplementary information is available at https://github.com/EpistasisLab/ASAREE/tree/main/publications/bioinformatics
Jay Moran, P. Freda, Attri Ghosh et al.· bioRxiv· 0 citations
The integration of Artificial Intelligence (AI) into IT Operations Management (ITOM), commonly referred to as AIOps, offers substantial potential for automating workflows, enhancing efficiency, and supporting informed decision-making. However, practical implementation of AI within IT operations remains challenging, particularly due to data quality issues, the complexity of cloud-native environments, and skill gaps within operational teams. The emergence of Large Language Models (LLMs) presents new opportunities to address these barriers by leveraging their advanced natural language understanding, enabling the analysis of unstructured data such as logs, incident reports, and technical documentation. In this paper, we present an industry experience report conducted on Red Hat OpenShift to explore how LLMs can be operationalized in real-world Kubernetes-based environments. We integrate predictive machine learning models with LLM agents through tool-augmented reasoning, highlighting novel methods to automate IT tasks, enhance observability, and reduce operator burden. Our findings provide insights into both the capabilities and limitations of LLMs in production-grade AIOps scenarios.
Arthur Vitui, T. Chen· SIGSOFT FSE Companion· 0 citations