{"slug": "agentic-world-action-models", "title": "Agentic World Action Models", "summary": "A paper submitted to arXiv on 21 October 2026 introduces AW-0, an agentic world action model framework that jointly models code, future video and robot actions as three coupled generative streams inside a unified mixture-of-transformers architecture. The authors report that AW-0, in which a code expert generates parameterized skill routines and control logic while video and action experts produce future visual states and low-level motor commands, outperformed vision-language-action (VLA) and world action model (WAM) baselines on RoboTwin 2.0 and physical bimanual manipulation tasks, with gains in language following, semantic reasoning and robustness. The work also includes an automated curation pipeline that labels robot and human video trajectories with aligned programs and consolidates recurring routines into reusable skill libraries.", "body_md": "# Computer Science > Robotics\n\n  [Submitted on 21 Oct 2026]\n\n# Title:Agentic World Action Models\n\n[View PDF](http://arxiv.org/pdf/2610.30136v1)\n\n[HTML (experimental)](https://arxiv.org/html/2610.30136v1)\n\nAbstract:Recent world action models provide visual foresight and future prediction for robot manipulation, but lack explicit mechanisms for compositional skill reuse. Agentic robotics combines code-based planning and reasoning with reusable skills, but often lacks predictive grounding in physical dynamics. We introduce AW-0, an agentic world action model framework that integrates code-based planning with joint video and action prediction. We jointly model code, future video, and robot actions as three coupled generative streams within a unified mixture-of-transformers architecture. Within this architecture a code expert generates parameterized skill routines and control logic while video and action experts generate future visual states and low-level motor commands. Code serves two complementary roles: it structures multi-step prediction and control within the world model and represents skills as reusable programs for subsequent agentic execution. We further introduce an automated curation pipeline that labels robot and human video trajectories with aligned programs and consolidates recurring routines into reusable skill libraries. Evaluations on RoboTwin 2.0 and physical bimanual manipulation tasks show improved task performance over VLA and WAM baselines, alongside gains in language following, semantic reasoning and robustness, demonstrating that agentic code enables connection between planning, prediction and execution within WAMs.\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))\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/agentic-world-action-models", "canonical_source": "http://arxiv.org/abs/2610.30136v1", "published_at": "2026-10-22 14:02:00+00:00", "updated_at": "2026-10-22 14:12:41.198313+00:00", "lang": "en", "topics": ["robotics", "ai-research", "machine-learning", "artificial-intelligence"], "entities": ["AW-0", "RoboTwin 2.0", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/agentic-world-action-models", "markdown": "https://wpnews.pro/news/agentic-world-action-models.md", "text": "https://wpnews.pro/news/agentic-world-action-models.txt", "jsonld": "https://wpnews.pro/news/agentic-world-action-models.jsonld"}}