SOURCE-LINKED INTELLIGENCE

PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Coding agents are beginning to act in the visual world. They now build webpages, GUIs, games, 3D scenes, diagrams, and documents. Success in such visual coding requires bridging two spaces: inferring visual structure and expressing it programmatically. Slides are a core medium of knowledge work, widely used to communicate ideas and collaborate in a form that people can directly inspect and edit. Therefore, they provide an ideal testbed for visual coding, as they require agents to recover visual structure and realize it as editable objects. However, existing benchmarks either rely on subjective

Read original source ↗ Open in workspace

recordType

paper

region

Global