Metraipolis › archive › dc_285a00adfbde
Evaluating Physically Grounded Procedural Reasoning in VLMs through Real-World Execution: Crochet as a Testbed — arXiv:2611.10740
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10740
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:44:29.799Z
- SHA-256 of the archived text
f2484eb95bcd88fd34745c2b0ec143e538d39a64d885d7dbe68a2dd4c91ba7a3- Stable URL of this page
https://metraipolis.com/documento/dc_285a00adfbde
How to cite
Evaluating Physically Grounded Procedural Reasoning in VLMs through Real-World Execution: Crochet as a Testbed — arXiv:2611.10740 — arXiv (en), https://arxiv.org/abs/2611.10740 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_285a00adfbde (Metraipolis archive dc_285a00adfbde, sha256 f2484eb95bcd88fd34745c2b0ec143e538d39a64d885d7dbe68a2dd4c91ba7a3)
BibTeX
@misc{dc285a00adfbde,
title = {Evaluating Physically Grounded Procedural Reasoning in VLMs through Real-World Execution: Crochet as a Testbed — arXiv:2611.10740},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10740},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_285a00adfbde; sha256 f2484eb95bcd88fd34745c2b0ec143e538d39a64d885d7dbe68a2dd4c91ba7a3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10740. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language Models (VLMs) can generate procedures that look convincing on paper, but do they work in practice? In this paper, we propose crochet as an ideal testbed for physically grounded procedural reasoning in VLMs. Crochet cannot be reliably simulated or automated: the only way to know what a pattern produces is to make it by hand, yet verification is tangible and cheap, requiring nothing but a hook and a ball of yarn. We introduce FoundationChain, a deceptively simple test of procedural reasoning: given an image of a basic crochet object, can VLMs infer how it was made and generate a pattern that produces the same result? We crochet 40 patterns generated by four VLMs by hand. Even at this scale, physical execution not only reveals failures that automated proxies cannot detect, but also enables a more precise diagnosis of their causes and consequences: while models write fluent, convincing patterns, only four are free of errors, and our analysis exposes deficiencies in visual, geometric and procedural reasoning. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.10740 — 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 2026-11-10T18:37:52.428Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).