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

ICLR 2026 Conference Submission25164 Authors

Keywords: Embodied Decision Making, LLM, Embodied Brain

TL;DR: EmboMatrix is a scalable, annotation-free training ground that aligns data, system, and RL algorithm design to enable autonomous environment exploration by LLMs, yielding consistent gains on embodied decision making benchmarks.

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 \textbf{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 \textbf{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. The code will be released upon the paper's acceptance.

Primary Area: applications to robotics, autonomy, planning

Submission Number: 25164