--- title: Smol2Operator: Post-Training GUI Agents for Computer Use description: Hugging Face introduces Smol2Operator, a comprehensive approach for training lightweight vision-language models to perform GUI automation tasks. The... canonical: https://daily.dev/posts/smol2operator-post-training-gui-agents-for-computer-use-jrjgqypri twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Smol2Operator: Post-Training GUI Agents for Computer Use | daily.dev og:description: Hugging Face introduces Smol2Operator, a comprehensive approach for training lightweight vision-language models to perform GUI automation tasks. The... og:url: https://daily.dev/posts/smol2operator-post-training-gui-agents-for-computer-use-jrjgqypri og:image: https://api.daily.dev/og/posts/jRjGQYPri.png og:image:alt: Smol2Operator: Post-Training GUI Agents for Computer Use og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Smol2Operator: Post-Training GUI Agents for Computer Use **[Hugging Face](https://daily.dev/sources/huggingface)** · 12 min read · 2 upvotes · 0 comments ## Summary Hugging Face introduces Smol2Operator, a comprehensive approach for training lightweight vision-language models to perform GUI automation tasks. The methodology transforms a base model with zero grounding capabilities into an agentic GUI coder through a two-phase training process. Phase 1 establishes GUI grounding using action-instruction pairs, while Phase 2 develops agentic reasoning capabilities. The approach achieves 61% accuracy on ScreenSpot-v2 benchmark and includes complete open-source training recipes, datasets, preprocessing tools, and the resulting model to enable full reproducibility. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Ai2 launches MolmoWeb, an open-source web agent](https://daily.dev/posts/ai2-launches-molmoweb-an-open-source-web-agent-ec7sqrixm) · The New Stack · 4 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#computer-vision](https://daily.dev/tags/computer-vision), [#huggingface](https://daily.dev/tags/huggingface), [#vlm](https://daily.dev/tags/vlm) [View this post on daily.dev](https://daily.dev/posts/smol2operator-post-training-gui-agents-for-computer-use-jrjgqypri) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Smol2Operator: Post-Training GUI Agents for Computer Use","url":"https://daily.dev/posts/smol2operator-post-training-gui-agents-for-computer-use-jrjgqypri","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/smol2operator-post-training-gui-agents-for-computer-use-jrjgqypri"},"datePublished":"2025-09-23T13:41:19.985Z","dateModified":"2025-09-23T13:41:44.027Z","description":"Hugging Face introduces Smol2Operator, a comprehensive approach for training lightweight vision-language models to perform GUI automation tasks. The...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0936a580b0bb961de54ac19c6e877954?_a=AQAEulh","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0936a580b0bb961de54ac19c6e877954?_a=AQAEulh","isAccessibleForFree":true,"articleSection":"Hugging Face","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hugging Face","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f1f55c67d81a4330acf5b90b26b0c8e1","url":"https://daily.dev/sources/huggingface"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/smol2operator-post-training-gui-agents-for-computer-use-jrjgqypri","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,computer-vision,huggingface,vlm","timeRequired":"PT12M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hugging Face","item":"https://daily.dev/sources/huggingface"},{"@type":"ListItem","position":3,"name":"Smol2Operator: Post-Training GUI Agents for Computer Use"}]} ```