[QA] Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

The paper identifies "underthinking" in LLMs, where frequent thought switching hampers reasoning depth. It proposes a new strategy to improve accuracy in complex tasks without model fine-tuning.
arxiv.org/abs/...
RUclips: / @arxivpapers
TikTok: / arxiv_papers
Apple Podcasts: podcasts.apple...
Spotify: podcasters.spo...