{"slug": "xstack-a-benchmark-for-ml-repo-migration", "title": "XStack: A Benchmark for ML Repo Migration", "summary": "A November 5, 2026 arXiv paper introduced XStack, a benchmark that grades AI agents on migrating machine learning repositories from PyTorch on NVIDIA GPUs to JAX on Google TPUs, with each agent given a PyTorch repository and a clean TPU machine and required to deliver a JAX repository that meets grading criteria based on the source repository's published result. Claude Opus 5 passed 75% of migrations, GPT-5.6-sol passed 45%, and every other agent passed at most 40%, showing agent-driven migration remains unreliable. The authors released XStack to make reliable cross-framework and cross-hardware migration measurable.", "body_md": "# Computer Science > Machine Learning\n\n  [Submitted on 5 Nov 2026]\n\n# Title:XStack: A Benchmark for ML Repo Migration\n\n[View PDF](http://arxiv.org/pdf/2611.08472v1)\n\n[HTML (experimental)](https://arxiv.org/html/2611.08472v1)\n\nAbstract:ML code should run where researchers choose, not where it was first written. Today, machine learning code mainly lives in two ecosystems, PyTorch on NVIDIA GPUs and JAX on Google TPUs. Migrating repositories between them means building and testing across frameworks and hardware. This migration is (1) a practical need, since it unlocks different hardware for researchers, and (2) a natural benchmark: it involves different frameworks and hardware, covers whole repositories, and is long-horizon and challenging. We introduce XStack, a benchmark that evaluates agents on migrating ML repositories between these two ecosystems. Each agent receives a PyTorch repository and a clean TPU machine and must deliver a JAX repository. Its output passes if it meets our grading criteria, based on the source repository's published result, authenticated and calibrated by us. Migration by agents remains unreliable: Claude Opus 5 passes 75%, GPT-5.6-sol 45%, and every other agent at most 40%. XStack is a step toward freeing ML code from its ecosystem. We release XStack to make progress toward reliable migration across frameworks and hardware measurable.\n    \n\n### Additional Features\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/xstack-a-benchmark-for-ml-repo-migration", "canonical_source": "http://arxiv.org/abs/2611.08472v1", "published_at": "2026-11-06 15:45:56+00:00", "updated_at": "2026-11-06 16:20:45.368945+00:00", "lang": "en", "topics": ["ai-research", "machine-learning", "ai-agents", "ai-tools", "large-language-models"], "entities": ["XStack", "Claude Opus 5", "GPT-5.6-sol", "PyTorch", "JAX", "NVIDIA", "Google TPUs", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/xstack-a-benchmark-for-ml-repo-migration", "markdown": "https://wpnews.pro/news/xstack-a-benchmark-for-ml-repo-migration.md", "text": "https://wpnews.pro/news/xstack-a-benchmark-for-ml-repo-migration.txt", "jsonld": "https://wpnews.pro/news/xstack-a-benchmark-for-ml-repo-migration.jsonld"}}