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

by DeepSeek · open-source · Last verified 2026-03-17

DeepSeek-R1 demonstrates that pure reinforcement learning with rule-based rewards—without supervised fine-tuning on chain-of-thought data—can incentivize emergent reasoning capabilities in LLMs including self-verification, reflection, and long chain-of-thought. The model achieves performance comparable to OpenAI-o1 on reasoning benchmarks while being fully open-sourced, triggering a significant industry response.