Home › Research Papers › DeepSeek-R1 — Reasoning via RL (2025)
DeepSeek-R1 — Reasoning via RL (2025)
Research Paper
Reasoning
The open recipe for reasoning models — a Nature cover, from a hedge fund's lab.
You're looking at a research-paper record: a landmark paper and what it introduced to the field.
The R1 report showed reasoning emerging from pure reinforcement learning on verifiable problems (R1-Zero), then a practical pipeline mixing SFT and RL — published openly with weights while Western labs kept their recipes closed. It democratized the o1 breakthrough within weeks and later ran as Nature's cover paper.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Introduced in
Related
Sources
Record reviewed as of 2026-01-15 — see Methodology.