EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lei, Zixing, Yin, Sheng, Xiong, Yichen, Ding, Yuanzhuo, Huang, Wenhao, Wei, Yuxi, Xu, Qingyao, Li, Yiming, Li, Weixin, Wang, Yunhong, Chen, Siheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915553130577920
author Lei, Zixing
Yin, Sheng
Xiong, Yichen
Ding, Yuanzhuo
Huang, Wenhao
Wei, Yuxi
Xu, Qingyao
Li, Yiming
Li, Weixin
Wang, Yunhong
Chen, Siheng
author_facet Lei, Zixing
Yin, Sheng
Xiong, Yichen
Ding, Yuanzhuo
Huang, Wenhao
Wei, Yuxi
Xu, Qingyao
Li, Yiming
Li, Weixin
Wang, Yunhong
Chen, Siheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12072
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making
Lei, Zixing
Yin, Sheng
Xiong, Yichen
Ding, Yuanzhuo
Huang, Wenhao
Wei, Yuxi
Xu, Qingyao
Li, Yiming
Li, Weixin
Wang, Yunhong
Chen, Siheng
Artificial Intelligence
Robotics
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.
title EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making
topic Artificial Intelligence
Robotics
url https://arxiv.org/abs/2510.12072