Better, Faster: Harnessing Self-Improvement in Large Reasoning Models 事件

Better, Faster: Harnessing Self-Improvement in Large Reasoning Models arXiv:2605.24998v1 Announce Type: new Abstract: Self-improvement training enables the large reasoning models (LRMs) to improve themselves by self-generating reasoning trajectories as training data without external supervision. However, we find that this method often falls short in complex reasoning tasks and even leads to model collapse. Through a series of preliminary analyses, we reveal two problems: (1) data imbalance, whe