Today for AI
HOT RADAR
agentHEAT 9.3°

AI CURATED HOT STORY · 10/24/2026

LiQing AI Releases PrismWAM and RoboDoctor to Advance Physical AI Scaling

1 reports archived1 independent sourcesupdated 10/24/2026, 12:30:00
Synthesis & Latest Updates
1 Sources Cross-Validated

LiQing AI released two Physical AI breakthroughs: the World Action Model PrismWAM, which ranks first on RoboTwin 2.0, and the Agentic framework RoboDoctor, leading in RoboDojo tests. The initiative shifts focus from 'Scaling Semantics' to 'Scaling Physics,' emphasizing physical state representation and execution feedback to enhance robotic interaction capabilities.

LATEST/LiQing AI released two Physical AI breakthroughs: the World Action Model PrismWAM, which ranks first on RoboTwin 2.0, and the Agentic framework RoboDoctor, leading in RoboDojo tests. The initiative shifts focus from 'Scaling Semantics' to 'Scaling Physics,' emphasizing physical state representation and execution feedback to enhance robotic interaction capabilities.

Hourly heat curve

2 fully observed hours
Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first
  1. 机器之心 (微信公众号)T2·68 pts

    LiQing AI Releases PrismWAM and RoboDoctor to Advance Physical AI Scaling

    • PrismWAM, a World Action Model, ranked first on RoboTwin 2.0 by focusing on physical state representation and prediction.
    • RoboDoctor, an Agentic framework, scored 57.1 on RoboDojo (covering 54 tasks), addressing execution diagnosis and continuous improvement.
    • The industry argues that the next phase of Physical AI scaling lies in 'Scaling Physics'—improving the conversion efficiency of data and compute into physical capabilities—rather than just expanding model size.
LiQing AI Releases PrismWAM and RoboDoctor to Advance Physical AI Scaling | Today for AI