Metraipolis › archive › dc_6f39ea6c910f

PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides — arXiv:2609.29718

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29718
License (as archived)
CC0-1.0
Archived
2026-10-08T04:27:44.277Z
SHA-256 of the archived text
80f9039b6ca679237fb1e39affd8568582f571940b328f8f55d74f5b8fd97633
Stable URL of this page
https://metraipolis.com/documento/dc_6f39ea6c910f

How to cite

PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides — arXiv:2609.29718 — arXiv (en), https://arxiv.org/abs/2609.29718 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6f39ea6c910f (Metraipolis archive dc_6f39ea6c910f, sha256 80f9039b6ca679237fb1e39affd8568582f571940b328f8f55d74f5b8fd97633)
BibTeX
@misc{dc6f39ea6c910f,
  title = {PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides — arXiv:2609.29718},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29718},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6f39ea6c910f; sha256 80f9039b6ca679237fb1e39affd8568582f571940b328f8f55d74f5b8fd97633},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29718. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Coding agents are increasingly moving beyond text-based software tasks to reconstruct visual targets through code. This capability, visual coding, requires agents to translate their understanding of visual targets into executable code. Slides provide a natural testbed for this capability, combining rich visual structure with objects that can be programmatically created and edited. To measure this capability, we introduce PPTBench, a benchmark for reconstructing scientific flow diagrams as editable PowerPoint slides. PPTBench covers 500 scientific flow-diagram tasks across 10 presentation domains, drawn from real research papers, and is evaluated with a four-stage agentic judge covering artifact validity, process and connector fidelity, rendering quality, and visual fidelity. Evaluation of ten models across 36 model--harness--effort configurations shows a substantial gap in reliable visual coding: the best configuration achieves 77.34, while the median across configurations is 24.38. Fine-grained analysis shows that agents can generally produce valid slide files, but struggle to produce high-quality reconstructions that faithfully recover the semantics and visual structure of the target. Further analysis shows that increasing reasoning effort primarily improves hard-gate passage rather than mean detail quality on each configuration's passing tasks, while configurations with more inspection tend to achieve higher overall scores. PPTBench establishes a measurable testbed for studying visual coding and advancing agents toward more reliable visual creation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.29718 — 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 2026-10-08T03:50:58.142Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).