Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models

ArXi:2604.05868v1 Announce Type: new Large Reasoning Models (LRMs) have shown remarkable performance on challenging questions, such as math and coding. However, to obtain a high quality solution, one may need to sample than once. In principal, there are two sampling strategies that can be composed to form complex processes: sequential sampling and parallel sampling. In this paper, we first compare these two approaches with rigor, and observe, aligned with previous works, that parallel sampling seems to outperform sequential sampling even though the latter should have representation power.