# DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

> scientific paper by DeepSeek Research introducing reinforcement learning techniques in the reasoning capabilities of large language models

**Wikidata**: [Q131920821](https://www.wikidata.org/wiki/Q131920821)  
**Source**: https://4ort.xyz/entity/deepseek-r1-incentivizing-reasoning-capability-in-llms-via-reinforcement-learning