Doing More With Less: Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling

arXiv:2604.25098v1 Announce Type: new Abstract: While current Large Language Models (LLMs) exhibit remarkable reasoning capabilities through test-time compute scaling (TTS), their massive parameter counts and high inference costs have motivated the development of pruning methods that can reduce model size without sacrificing performance. However, specific to reasoning LLMs, prior work has shown that structured pruning (methods which removes entire set of layer blocks), significantly degrades TTS