Agentic visual analytics (VA) represents an emerging class of systems in which large language model (LLM)-driven agents autonomously plan, execute, evaluate, and iterate across the full visual analytics pipeline. By shifting users from low-level tool operations to high-level analytical goals expressed through natural language, these systems are fundamentally transforming how humans interact with data. However, the rapid proliferation of such systems in recent years has outpaced our understanding of their design landscape. Two intertwined problems remain open: how do autonomous agents reshape the traditional VA pipeline, and how must human involvement adapt as agent autonomy increases? To address these questions, this paper presents a comprehensive survey of 55 primary agentic VA systems and introduces a co-evolutionary framework. This framework is essential because it jointly analyzes the progression of agent autonomy alongside the necessary shift in human roles from manual operators to strategic supervisors. Within this framework, we define a role-workflow taxonomy that aligns four key agentic roles (PLANNER, CREATOR, REVIEWER, and CONTEXT MANAGER) and maps them onto established VA pipeline stages. Our analysis uncovers recurring trade-offs along three foundational axes: autonomy levels, agentic roles, and the VA workflow. We consolidate these findings into actionable design guidelines and outline future research directions for agentic visual analytics. A web-based interactive browser of our co-evolutionary framework, including the corpus and design guidelines, is available at agenticva.github.io/AgenticVA/.

翻译：代理视觉分析（VA）代表了一类新兴系统，其中由大语言模型（LLM）驱动的代理能够自主规划、执行、评估并迭代完成完整的视觉分析流程。通过将用户从低层级工具操作转移到用自然语言表达的高层级分析目标，这些系统正在从根本上改变人类与数据交互的方式。然而，近年来此类系统的快速 proliferation 已超越了我们对其设计空间的理解。两个相互交织的问题仍未解决：自主代理如何重塑传统VA流程？随着代理自主性的提升，人类参与方式又必须如何调整？为回答这些问题，本文对55个主要代理VA系统进行了全面综述，并提出了一个协同演化框架。该框架的关键在于联合分析代理自主性的演进过程，以及人类角色从手动操作者向战略监督者的必要转变。在此框架内，我们定义了一个角色-工作流分类体系，将四种核心代理角色（规划者、创造者、评审者与上下文管理者）与既定的VA流程阶段进行对齐。我们的分析揭示了沿三个基础轴（自主性层级、代理角色与VA工作流）反复出现的权衡关系。我们将这些发现整合为可操作的设计指南，并概述了代理视觉分析未来的研究方向。本协同演化框架的网页交互式浏览器（包含语料库与设计指南）可通过agenticva.github.io/AgenticVA/访问。