LimX Dynamics has demonstrated its full-size humanoid robot, Oli, autonomously completing a sequence of household tasks in a real home environment without teleoperation or post-production editing1. The 31-degree-of-freedom robot continuously performed clothes folding, item organization, box stacking, trash pickup, and water delivery in a single uninterrupted take. The demonstration places LimX as the second company globally, alongside Figure, to achieve this level of autonomous long-horizon household manipulation, according to Pandaily.
The COSA architecture
The capability is driven by COSA 0.5, a control architecture that LimX describes as "counter-consensus" because it explicitly rejects the prevailing industry approach of treating a single large model as the robot's brain. Founder Zhang Wei argued that equating a large model with brain function is misleading, comparing a pure large model to "Stephen Hawking lying in bed: extremely intelligent but completely unable to move".
COSA implements a three-tier S2-S1-S0 architecture operating at different time scales. The S2 Cognition Layer functions as a prefrontal cortex analog, using an LLM/VLM agent for scene understanding, memory, world modeling, reasoning, and human interaction — it decides what to do. The S1 Skill Layer provides a portfolio of trained capabilities, including vision-language-action models for whole-body motion generation. The S0 Motion Control Layer runs a 10-million-parameter whole-body transformer policy at 1,000 Hz on-device.
The three layers communicate through intentionally narrow interfaces, with intent flowing downward and robot state flowing upward asynchronously without blocking. Each layer can be independently upgraded, replaced, or fine-tuned without affecting the others.
Training on the real robot
The Oli demonstration relied on real-robot reinforcement learning with expert teleoperation corrections, independent balance maintenance by S0, corrected-data training of reward models, and RL iteration on the physical robot. LimX says the system gets stronger with continued use rather than freezing after initial training.
LimX says the COSA 0.5 capability unlock makes its consumer-facing strategy increasingly credible. CEO Zhang Wei positions humanoids for commercial, hospitality, entertainment, and household service markets.
ANALYSIS The modular, layered design carries a practical implication: decoupling high-level reasoning from low-level motor control means LimX can swap in newer foundation models at the S2 tier or retrain locomotion policies at S0 without requalifying the full stack. Whether the single-take household demonstration translates to the reliability required for consumer deployment remains an open question, but the architectural separation between cognition, skill, and motion control offers a distinct engineering path from the end-to-end model approaches pursued elsewhere in the industry.