SOURCE-LINKED INTELLIGENCE

VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphics

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Converting scientific graphics into editable representations remains a challenging problem for image-to-code generation because of their heterogeneous elements and complex layouts. Recent multi-agent reconstruction systems have advanced this line of work, but often follow a copy-paste paradigm: the reconstructed image closely resembles the original, while complex regions remain effectively uneditable. We instead formulate a different objective, raster-to-authoring reconstruction, which aims to recover an authoring representation that supports native, customized editing rather than mere visual

Read original source ↗ Open in workspace

recordType

paper

region

Global