{"slug": "embodiedevo-self-improving-coding-agents-for-physical-intelligence", "title": "EmbodiedEvo: Self-improving Coding Agents for Physical Intelligence", "summary": "A team led by Wenyi Li submitted EmbodiedEvo, a self-improving coding agent for physical tasks, to arXiv on 13 Oct 2026 (latest version 14 Oct 2026), reporting an average score of 44.48 and a 37.82% success rate on RoboDojo-Sim, surpassing all officially verified results. The system evolves reusable Skills and Lessons through feedback on a single Playground scene, then freezes the resulting harness for new scenes; experience from the stronger Astra model raised Sol and Luna's success rates by 8.86 and 5.50 percentage points over no experience, and Skills and Lessons achieved comparable task performance at 53.0% lower execution cost than raw interaction history. Paired tests showed the largest gains on memory-dependent tasks and successful reuse of coordinated procedures, while fine contact control remained difficult.", "body_md": "# Computer Science > Robotics\n\n  [Submitted on 13 Oct 2026 (this version), \n\n*latest version 14 Oct 2026*([v2](https://arxiv.org/abs/2610.18867v2))]\n# Title:EmbodiedEvo: Self-improving Coding Agents for Physical Intelligence\n\n[View PDF](http://arxiv.org/pdf/2610.18867v1)\n\n[HTML (experimental)](https://arxiv.org/html/2610.18867v1)\n\nAbstract:Bringing general-purpose agents into the physical world calls for an executable representation of physical intelligence. Compared with vision-language-action (VLA) models, which map observations and language instructions directly to actions, code makes control logic explicit and reusable. Code can serve not only as a policy representation but also as the workspace in which the agent solves a task. Rather than following a prescribed workflow of planning, execution, and verification, the agent can autonomously inspect the state, revise and execute code, and use feedback to choose the next step. The success of this SWE-style loop in digital environments motivates its extension to physical tasks. Yet physical execution remains prone to recurring failures. To retain and refine experience for later scenes, we introduce EmbodiedEvo, where a coding agent evolves reusable Skills and Lessons through feedback on a single Playground scene, then freezes the resulting harness for diverse new scenes. On RoboDojo-Sim, EmbodiedEvo achieves an average score of 44.48 and a success rate of 37.82\\%, surpassing all officially verified results. Paired tests show the largest gains on memory-dependent tasks and successful reuse of coordinated procedures, while fine contact control remains difficult. Experience from stronger models also improves weaker executors: Astra's experience raises Sol and Luna's success rates by 8.86 and 5.50 percentage points over no experience. Compared with raw interaction history, Skills and Lessons achieve comparable task performance at 53.0\\% lower execution cost.\n    \n\n## Submission history\n\nFrom: Wenyi Li [\n[view email](http://arxiv.org/show-email/0abc43c8/2610.18867)]\n\n**[v1]** Tue, 13 Oct 2026 17:59:51 UTC (13,771 KB)\n\n**Wed, 14 Oct 2026 17:45:55 UTC (13,742 KB)**\n\n[\\[v2\\]](http://arxiv.org/abs/2610.18867v2)\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/embodiedevo-self-improving-coding-agents-for-physical-intelligence", "canonical_source": "http://arxiv.org/abs/2610.18867v1", "published_at": "2026-10-14 14:20:21+00:00", "updated_at": "2026-10-15 04:53:22.576194+00:00", "lang": "en", "topics": ["robotics", "ai-agents", "ai-research", "machine-learning", "artificial-intelligence"], "entities": ["EmbodiedEvo", "Wenyi Li", "RoboDojo-Sim", "Astra", "Sol", "Luna", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/embodiedevo-self-improving-coding-agents-for-physical-intelligence", "markdown": "https://wpnews.pro/news/embodiedevo-self-improving-coding-agents-for-physical-intelligence.md", "text": "https://wpnews.pro/news/embodiedevo-self-improving-coding-agents-for-physical-intelligence.txt", "jsonld": "https://wpnews.pro/news/embodiedevo-self-improving-coding-agents-for-physical-intelligence.jsonld"}}