Symbol b

The passage around this formula

Consider a task instance with a policy $\pi_\theta$ and a compute budget b spent at inference, whether as sequential deliberation, parallel sampling, or search against a verifier. Expected quality is some q(b) that rises and saturates. Snell and colleagues studied this directly and reported that allocating test-time compute adaptively to the difficulty of the prompt substantially outperforms uniform allocation, and that in some regimes additional inference compute is a more effective use of a marginal FLOP than additional parameters [ 9 ] . The practically important half of that finding is the first: the optimal b is a function of the instance, not of the model.

Read this part in the article →