Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Paper • 2501.18585 • Published 24 days ago • 55
LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters! Paper • 2502.07374 • Published 12 days ago • 33
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Paper • 2502.06703 • Published 13 days ago • 134