Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression

Excerpt

arXiv:2510.01581v2 Announce Type: replace Abstract: Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in line with task difficulty. On one hand, short reasoning (underthinking) leads to errors on harder problems that require extended reasoning steps; but, excessively long reasoning (overthinking) can be token-inefficient by generating unnecessary steps even after reaching a correct intermediate solution. We re