InfoEdit: Probing Global Layout Reasoning in Infographic Editing

Presented at the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), held October 24–29, 2026 in Budapest, Hungary.

Project Homepage · Paper · Code · Dataset

A user asks an image editor to insert a missing step into an infographic; neighboring nodes and connectors must reflow.
A typical “vibe-design” workflow with structured visual content. The instruction names one element, but the surrounding nodes and connectors must reflow for the result to be usable.

Abstract

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 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.

InfoEdit overview: eight logical-relation families, four editing tasks, and evaluation of edit compliance and content preservation.
Overview of InfoEdit: eight logical-relation families, four editing tasks, and a reflow-aware evaluation that checks both edit compliance and content preservation.
An InfoEdit Process infographic example with an editing instruction and expected and unexpected results.
A Process infographic example from the project page, illustrating the instruction and expected versus unexpected edits.

Read more on the Project Homepage.