为科学可视化设计可复用智能体技能，提升任务完成率与效率
SciVisAgentSkills: Design and Evaluation of Agent Skills for Scientific Data Analysis and Visualization
- 构建针对ParaView等工具的领域专用技能库，融合工具使用模式与领域知识
- 在108个多步骤任务上测试，技能使平均任务得分显著提升
- 适合科研人员与可视化开发人员，尤其关注长流程自动化工作流
近期基于智能体的可视化技术实现了自然语言到可执行科学可视化（SciVis）工作流的转换。尽管通用编码智能体能力较强，但在科学可视化任务中常缺乏特定工具的专业知识。本文提出SciVisAgentSkills，一个包含可复用智能体技能的集合，通过编码环境假设、工具使用模式及领域启发式规则，增强编码智能体在ParaView、napari、VMD和TTK等科学工具上的表现。我们在SciVisAgentBench基准（108个专家设计的多步骤任务）上评估了这些技能在Codex和Claude Code上的效果。结果表明，引入技能后任务平均得分提升，且具备一定的令牌效率优势，该优势取决于智能体调用方式与工具配置。研究强调了结构化程序知识对实现可靠、长周期科学可视化工作流的重要性，同时指出技能需与其执行宿主环境共同研究。代码已开源：https://github.com/KuangshiAi/SciVisAgentSkills。
原文摘要 · Abstract (English)
Recent advances in agentic visualization have enabled the translation of natural language into executable scientific visualization (SciVis) workflows. While general-purpose coding agents show strong capabilities, they often lack the tool-specific expertise required for SciVis tasks. In this work, we present SciVisAgentSkills, a collection of reusable agent skills that augment coding agents for scientific data analysis and visualization by encoding environment assumptions, tool usage patterns, and domain heuristics across scientific tools such as ParaView, napari, VMD, and TTK. We evaluate these skills on Codex and Claude Code using SciVisAgentBench, a benchmark of 108 expert-designed multi-step tasks. Results show that agent skills improve mean task scores across the evaluated suites, with token-efficiency benefits that depend on the agent harness and tool setting. These findings highlight the importance of structured procedural knowledge for enabling reliable, long-horizon SciVis workflows, while also showing that skills should be studied alongside the execution harness that loads and applies them. The skills are available at https://github.com/KuangshiAi/SciVisAgentSkills.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。