Metraipolis › archive › dc_11afd404cc45

InfoEdit: Probing Global Layout Reasoning in Infographic Editing — arXiv:2609.33286

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33286
License (as archived)
CC0-1.0
Archived
2026-10-07T21:54:01.123Z
SHA-256 of the archived text
c8ec76216fcc96564b8cfac91e005aceab521363c1c1f09ea71aa54469915b7e
Stable URL of this page
https://metraipolis.com/documento/dc_11afd404cc45

How to cite

InfoEdit: Probing Global Layout Reasoning in Infographic Editing — arXiv:2609.33286 — arXiv (en), https://arxiv.org/abs/2609.33286 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_11afd404cc45 (Metraipolis archive dc_11afd404cc45, sha256 c8ec76216fcc96564b8cfac91e005aceab521363c1c1f09ea71aa54469915b7e)
BibTeX
@misc{dc11afd404cc45,
  title = {InfoEdit: Probing Global Layout Reasoning in Infographic Editing — arXiv:2609.33286},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33286},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_11afd404cc45; sha256 c8ec76216fcc96564b8cfac91e005aceab521363c1c1f09ea71aa54469915b7e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33286. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal foundation models edit natural photographs at production quality, yet the same models struggle with structured visual content such as infographics. Unlike photographs, infographics encode information through logical relations; editing one element often requires surrounding elements to be adapted. We refer to this global layout reasoning capability as reflow. Existing image-editing benchmarks neither provide a dedicated setting for structured visual content nor evaluate the reflow capability. We introduce InfoEdit, a novel benchmark of 1,000 infographics across eight logical-relation families, paired with 4,000 editing instructions across four editing tasks, and a reflow-aware evaluation protocol. Across eight frontier editors, only GPT-Image-2 clears 60% average success rate; most models fall below 7%, and no editor exceeds 36% on the Swap-Block task even with perfect target localization. We further show that code-level editing can match the strongest pixel-level editor, revealing complementary strengths across tasks. InfoEdit identifies reflow as a central challenge in structured visual content editing and provides a diagnostic benchmark to facilitate future progress.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.33286 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T21:27:08.757Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).