A survey of 55 agentic VA systems proposes a co-evolutionary framework defining four agent roles (PLANNER, CREATOR, REVIEWER, CONTEXT MANAGER) mapped to visual analytics pipeline stages along with design guidelines.
Nli4volvis: Natural language interaction for volume visualization via llm multi-agents and editable 3d gaussian splatting
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
Raiven mediates LLM visualization authoring via a formally defined DSL that unifies scientific and information visualization, producing deterministic, verifiable code from metadata-only inputs.
SASAV introduces the first fully autonomous multi-agent system for scientific data analysis and visualization that operates without external prompting or human-in-the-loop feedback.
Topo-GS repurposes 3D Gaussian Splatting with local geometric constraints and topology-aware losses to produce continuous volumetric embeddings of high-dimensional data.
General-purpose coding agents achieve highest success on SciVis tasks but cost more compute, while domain-specific agents are efficient yet less flexible and computer-use agents falter on long workflows.
citing papers explorer
-
Exploring Agentic Visual Analytics: A Co-Evolutionary Framework of Roles and Workflows
A survey of 55 agentic VA systems proposes a co-evolutionary framework defining four agent roles (PLANNER, CREATOR, REVIEWER, CONTEXT MANAGER) mapped to visual analytics pipeline stages along with design guidelines.
-
Raiven: LLM-Based Visualization Authoring via Domain-Specific Language Mediation
Raiven mediates LLM visualization authoring via a formally defined DSL that unifies scientific and information visualization, producing deterministic, verifiable code from metadata-only inputs.
-
SASAV: Self-Directed Agent for Scientific Analysis and Visualization
SASAV introduces the first fully autonomous multi-agent system for scientific data analysis and visualization that operates without external prompting or human-in-the-loop feedback.
-
Topo-GS: Continuous Volumetric Embedding of High-Dimensional Data via Topological Gaussian Splatting
Topo-GS repurposes 3D Gaussian Splatting with local geometric constraints and topology-aware losses to produce continuous volumetric embeddings of high-dimensional data.
-
Exploring Interaction Paradigms for LLM Agents in Scientific Visualization
General-purpose coding agents achieve highest success on SciVis tasks but cost more compute, while domain-specific agents are efficient yet less flexible and computer-use agents falter on long workflows.