Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
We study a novel language model architecture that is capable of scaling test-time computation by implicitly reasoning in latent space. Our model works by iterating a recurrent block, thereby unrolling to arbitrary depth at test-time. This stands in contrast to mainstream reasoning models that scale up compute by producing more tokens. Unlike approaches based on chain-of-thought, our approach does not require any specialized training data, can work with small context windows, and can capture types of reasoning that are not easily represented in words. We scale a proof-of-concept model to 3.5 billion parameters and 800 billion tokens. We show that the resulting model can improve its performance on reasoning benchmarks, sometimes dramatically, up to a computation load equivalent to 50 billion parameters.
PDF Abstract
MMLU
GSM8K
HumanEval
HellaSwag
PIQA
WinoGrande
OpenBookQA
WebText
SciQ
ARC (AI2 Reasoning Challenge)
MathQA
