Carnegie Mellon University

Trends

• Robotics and world models attract capital on the way to deployment

Items

1. Aug 28

   CMU's R³ teaches robots to reason in language

   A post-training recipe mid-trains off-the-shelf VLMs on reasoning traces, then applies single-step, rubric-based RL from offline action data, using free-form language as test-time compute to steer low-level manipulation and improve exploration and generalization.

2. Jun 22

   CMU limits agents' role in causal discovery

   Argues agents should inspect data, retrieve context, and explain assumptions but never supply edges, priors, or causal conclusions, building the principle into the causal-learn+ platform so LLM unreliability is not laundered into causal evidence.