When Does Test-Time Search Help World Action Models? An Empirical Audit of Candidate Selection and Simulator Integrity
World-action models increasingly apply test-time scaling, spending extra inference computation on candidate selection and adaptive allocation to improve control. Such gains are credible only when candidates carry exploitable signal, nominal compute savings become real speedup, and evaluation stays reliable. We audit all three on Cosmos Policy and RoboCasa with a premise-first, pre-registered…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
