DeepSeek-R1: Incentivizing Reasoning via RL (arXiv 2501.12948)
by DeepSeek
Study the reported reinforcement-learning recipe behind DeepSeek-R1.
DeepSeek describes how reinforcement learning can develop reasoning behavior and how the resulting models are further refined. Treat the paper as a research account with specific experiments, not a guarantee that its results transfer to another training setup.
- Level
- Expert
- Models
- any
- Category
- Model Training
- Tags
- Source date
- date not stated
- Added
- 2026-10-18
- Last verified
- 2026-10-18
- Status
- ok
- Prerequisites
- Acts on model-training, infrastructure or research tooling; requires training-stack expertise.
- Subcategory
- post training rl
- Region
- CN
- Original language
- en
- Access
- free
- Resource reuse
- closed: No general open-reuse grant established from the inspected page. Closed is the conservative index bucket, not a legal finding; the resource is publicly readable. Facet definitions
Summary in our own words. Rights remain with the original creator. Credit and correction policy.