Metraipolis › archive › dc_ff01e922811f

FigmaTrace: Capturing Creative Nuances in Human Figma Design Workflows — arXiv:2608.21460

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21460
License (as archived)
CC0-1.0
Archived
2026-10-18T07:42:14.883Z
SHA-256 of the archived text
dab6082c7a686a97f9a038dc9ffaab9f0c91f2bb998c17c65a96bceb5d09d291
Stable URL of this page
https://metraipolis.com/documento/dc_ff01e922811f

How to cite

FigmaTrace: Capturing Creative Nuances in Human Figma Design Workflows — arXiv:2608.21460 — arXiv (en), https://arxiv.org/abs/2608.21460 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff01e922811f (Metraipolis archive dc_ff01e922811f, sha256 dab6082c7a686a97f9a038dc9ffaab9f0c91f2bb998c17c65a96bceb5d09d291)
BibTeX
@misc{dcff01e922811f,
  title = {FigmaTrace: Capturing Creative Nuances in Human Figma Design Workflows — arXiv:2608.21460},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21460},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff01e922811f; sha256 dab6082c7a686a97f9a038dc9ffaab9f0c91f2bb998c17c65a96bceb5d09d291},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21460. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision Language Models have recently shown improvements in several objective and verifiable domains such as object detection but continue to underperform on subjective and creative design tasks. A major contributor to this performance gap is the lack of high quality human workflow data that captures a diverse set of preferences and decisions that make human experts good at design tasks. In this work, we first define a unique, expert curated taxonomy of design skills and best practices which we further expand into a set of 126 open ended, subjective, long horizon tasks. Built on top of this and expert solutions, our dataset FigmaTrace contains over 200 hours of human captured video data converted into 3469 design trajectories using a novel design phase-based method. We use our dataset to train four models and show that training on FigmaTrace leads to a performance improvement comparable to frontier closed models such as \textsc{Claude-Opus-5} and \textsc{GPT-5.6-Sol} on four out of distribution agentic GUI environments. We further perform a useful ablation to attribute these performance improvements to a design phase-based video to trajectory conversion which outperforms prior length-based conversion approaches. Finally, we perform a qualitative analysis on the best performing \textsc{Qwen3.8-27B} outputs to better correlate performance improvements to FigmaTrace's trends. We open source our dataset and the best model for the community.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.21460 — 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 2026-10-18T07:37:52.812Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).