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.
Introducing computer use, a new Claude 3.5 Son- net, and Claude 3.5 Haiku
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.