李飞飞（FeiFei Li）最新论文：s1 开源推理大模型：简单的测试时间缩放 s1: Simple test-time scaling

s1: Simple test-time scaling

Minimal recipe for test-time scaling and strong reasoning performance matching o1-preview with just 1,000 examples & budget forcing

Pager:
https://arxiv.org/pdf/2501.19393

Test-time scaling is a promising new approach to language modeling that uses extra test-time compute
to improve performance. Recently, OpenAI’s o1 model showed this capability but did not publicly
share its methodology, leading to many replication efforts. We seek the simplest approach to achieve test-time scaling and strong reasoning performance.

First, we curate a small dataset s1K of 1,000 questions paired with reasoning traces relying on three criteria we validate through ablations: difficulty, diversity, and quality.

Second, we develop budget forcing to control test-time compute by forcefully terminating the model’s thinking
process or lengthening it by appending “Wait” multiple times to the model’s generation when it
tries to end. This ca