{"ID":2855493,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12072","arxiv_id":"2510.12072","title":"EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making","abstract":"Embodied decision-making enables agents to translate high-level goals into executable actions through continuous interactions within the physical world, forming a cornerstone of general-purpose embodied intelligence. Large language models (LLMs), with their general decision-making capabilities, offer a promising path to realize this potential; however, LLMs trained solely on language lack exposure to physical environments, limiting their true embodied understanding. To bridge this gap, we propose the concept of a training ground: a comprehensive infrastructure that provides task and scene simulation, embodied interaction, and feedback signals, offering a one-stop solution for LLM acquire genuine embodied decision-making skills. In this work, we present EmboMatrix, the first training ground of its kind, providing massive and diverse tasks with efficient simulation and precise rewards. EmboMatrix incorporates a series of novel techniques: a multi-agent data engine for large-scale task and scene generation, a distributed heterogeneous-hardware system for scalable simulation, and a multi-level reward architecture for precise supervision. Leveraging EmboMatrix, we cultivate EmboBrain, an LLM whose embodied decision-making abilities emerge from extensive embodied interactions. Experiments show that EmboBrain-7B surpasses the 671B DeepSeek-R1 baseline by 9.5\\% on two challenging embodied decision-making benchmarks, demonstrating the power of interactive, environment-grounded learning for building truly intelligent embodied agents.","short_abstract":"Embodied decision-making enables agents to translate high-level goals into executable actions through continuous interactions within the physical world, forming a cornerstone of general-purpose embodied intelligence. Large language models (LLMs), with their general decision-making capabilities, offer a promising path t...","url_abs":"https://arxiv.org/abs/2510.12072","url_pdf":"https://arxiv.org/pdf/2510.12072v1","authors":"[\"Zixing Lei\",\"Sheng Yin\",\"Yichen Xiong\",\"Yuanzhuo Ding\",\"Wenhao Huang\",\"Yuxi Wei\",\"Qingyao Xu\",\"Yiming Li\",\"Weixin Li\",\"Yunhong Wang\",\"Siheng Chen\"]","published":"2025-10-14T02:26:52Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.RO\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}