Exploring Agentic Visual Analytics: A Co-Evolutionary Framework of Roles and Workflows

2026-04-17

AI Summary

This study investigates how autonomous agents reconfigure traditional visual analytics workflows and reveals the evolving role of humans—from operators to strategic supervisors—as agent autonomy increases. Through a systematic review of 55 agent-driven visual analytics systems, the work proposes the first co-evolutionary framework that aligns agent roles (planner, creator, reviewer, context manager) with stages of the visual analytics process, elucidating a triadic trade-off among autonomy, human roles, and analytical workflow. The contributions include a role-process taxonomy, actionable design guidelines, and an online interactive framework explorer (agenticva.github.io/AgenticVA/), collectively offering both theoretical grounding and practical pathways for designing agent-augmented visual analytics systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Modeling other Agents
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

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/.

Problem

• Agentic Visual Analytics
• Agent Autonomy
• Human Roles
• Visual Analytics Pipeline
• Co-evolutionary Framework

Innovation

• Agentic Visual Analytics
• Co-evolutionary Framework
• Role-Workflow Taxonomy
• LLM-driven Agents
• Human-AI Collaboration