The paper introduces ATWL, a declarative language that formalizes visual analytics workflows by specifying typed artifacts and transforms with defined analytical intents and actors. A library of 54 workflows, curated from published papers with LLM assistance, demonstrates patterns such as human-machine labor division and refinement cycles. Experiments show that using ATWL and the library improves LLM-designed workflows, though branching remains a limitation requiring syntax extension.
arXiv:2607. 00969v1 Announce Type: cross Abstract: Visual analytics (VA) plays an increasingly important role in supporting machine learning (ML) workflows.
arXiv:2606. 31311v1 Announce Type: cross Abstract: Testing a new visual-analytics idea usually takes months: one needs to find a realistic data set, clean it, and implement an interactive prototype.
arXiv:2607. 16617v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts.
arXiv:2608. 11022v1 Announce Type: cross Abstract: Model Cards and Data Cards have demonstrated the value of structured, human-readable documentation for machine learning artifacts, capturing their context, parameters, limitations, and intended use.
arXiv:2606. 09239v1 Announce Type: new Abstract: While visual programming of data analysis workflows has become an important vehicle for the democratization of data science, such systems remain largely confined to standalone applications and offer limited support for transitioning their visual analytics solutions into interactive web environments.
arXiv:2607. 01709v1 Announce Type: new Abstract: Agents are increasingly used to construct workflows and assist humans in completing recurring tasks more efficiently.
TopoPilot is an agentic framework designed to automate complex scientific visualization workflows, particularly in topological data analysis and visualization. It uses a two‑agent architecture—a user‑prompt orchestrator and a verifier—to translate natural language into atomic backend actions and ensure semantic consistency before execution. The system incorporates deterministic guardrails and a taxonomy of failure modes, achieving over 95% success in 1,000 simulated multi‑turn conversations and outperforming baseline models and other code generation tools in accuracy, completion time, and token usage.
The paper introduces KNOWS, a benchmark for evaluating web agents that act as assistants by retrieving, synthesizing, and presenting information across complex, multi-step browser tasks. It outlines a task design rubric, evaluation protocol combining deterministic checks with LLM judgments, and reports that current agents achieve only modest success, with the best performing agent succeeding on less than 3% of tasks. The study highlights significant gaps in agents’ tool use, visual understanding, and long‑horizon reasoning.
arXiv:2609.24094v1 Announce Type: cross Abstract: Visual analytics (VA) enables sensemaking through interactive visualization, but effective analysis often requires experts to translate high-level in...
arXiv:2606. 18425v1 Announce Type: cross Abstract: Scientific workflow management systems (WMS) support scalable and reproducible execution of complex pipelines, but workflow design, implementation, and debugging remain largely manual and require significant expertise.
arXiv:2604. 26258v3 Announce Type: replace-cross Abstract: LLM workflows, which coordinate structured calls to individual LLMs/agents to achieve a particular goal, offer a promising path towards building powerful AI systems that can tackle diverse tasks.
arXiv:2608. 10039v1 Announce Type: new Abstract: Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), tools, and control logic into explicit execution structures.