Adaptive Parallel Reasoning: The Next Paradigm in Efficient Inference Scaling
Source
bair.berkeley.edu
Date
Terms in this piece · Glossary
test-time compute — Spending more computation when the model answers — thinking longer, trying multiple attempts — to buy accuracy without training a bigger model.
chain-of-thought — Having a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.
Why it matters
It describes a self-directed alternative to fixed chain-of-thoughtHaving a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.Full definition → scaling, directly relevant to anyone building or optimizing reasoning-heavy agents under compute or latency constraints.
