DeepSeek-R1
DeepSeek-R1 — reasoning ability emerges from pure RL
Why it matters
Proved that reasoning ability is not a secret recipe of closed labs; self-checking, re-examination and strategy switching emerged. The same report also published the RLVR recipe and a recipe for transferring the capability to small models
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2501.12948Added in Week 35, 2026 · See that week