{"slug": "watch-recall-act-always-on-robots-in-concurrent-embodied-streams", "title": "Watch, Recall, Act: Always-On Robots in Concurrent Embodied Streams", "summary": "A September 23, 2026 arXiv paper introduces ARMS (Always-on Robot in Multi-modal Streams), a streaming policy built on a single pretrained π0.5 backbone plus three lightweight modules that let a dual-arm robot watch live perception, recall its own past actions, and act concurrently. Trained on the ARMS Dataset, whose staged construction script labels every module from real dual-arm teleoperation, ARMS reaches 45% on the combined task versus 28% for the strongest of four main baselines, with ablations confirming the memory module, embodied-state head, and asynchronous concurrency are each necessary.", "body_md": "# Computer Science > Robotics\n\n  [Submitted on 23 Sep 2026]\n\n# Title:Watch, Recall, Act: Always-On Robots in Concurrent Embodied Streams\n\n[View PDF](http://arxiv.org/pdf/2609.28429v1)\n\n[HTML (experimental)](https://arxiv.org/html/2609.28429v1)\n\nAbstract:An always-on robot faces an endless stream that never resets: instructions arrive and lapse, the scene changes, and its own past actions reshape what it must reason about. Today's action models are built for the opposite: a fixed instruction, no mid-task intervention, single-step reasoning. In an open-ended world a robot must watch a live stream for far-future cues, recall its own far-past actions, and act on them under dual-arm concurrency. We present ARMS (Always-on Robot in Multi-modal Streams), a deliberately simple streaming policy: a single pretrained $\\pi$0.5 backbone augmented by three lightweight modules that turn live perception, embodied states, and the robot's own past actions into context the backbone reads before it acts. The modules update this context asynchronously, so watching and recalling never block acting and the two arms act at once. Rather than inventing new mechanisms, ARMS integrates these learned context providers with an agent-causal self-history that logs which arm did what, and when. To supervise them without extra annotation, we build ARMS Dataset, whose staged construction script itself labels every module from real dual-arm teleoperation. Trained on it, ARMS reaches 45% on the combined task against 28% for the strongest of our four main baselines, and ablations confirm the memory module, the embodied-state head, and asynchronous concurrency are each necessary.\n    \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/watch-recall-act-always-on-robots-in-concurrent-embodied-streams", "canonical_source": "http://arxiv.org/abs/2609.28429v1", "published_at": "2026-09-24 14:09:12+00:00", "updated_at": "2026-09-24 14:31:15.764322+00:00", "lang": "en", "topics": ["robotics", "machine-learning", "artificial-intelligence", "ai-research"], "entities": ["ARMS", "ARMS Dataset", "π0.5", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/watch-recall-act-always-on-robots-in-concurrent-embodied-streams", "markdown": "https://wpnews.pro/news/watch-recall-act-always-on-robots-in-concurrent-embodied-streams.md", "text": "https://wpnews.pro/news/watch-recall-act-always-on-robots-in-concurrent-embodied-streams.txt", "jsonld": "https://wpnews.pro/news/watch-recall-act-always-on-robots-in-concurrent-embodied-streams.jsonld"}}