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

Authors: DeepSeek-AI (2025)

arXiv: 2501.12948

TLDR (English)

DeepSeek-R1 shows that o1-like chain-of-thought reasoning can emerge purely from reinforcement learning (without supervised fine-tuning warmup), using GRPO instead of PPO. Fully open-source (weights + training details), it matches OpenAI o1 on multiple reasoning benchmarks and is one of the most significant open-source LLM results of 2025.

TLDR（中文）

DeepSeek-R1 展示了纯粹通过强化学习（无监督微调启动）就能涌现出类 o1 的链式推理能力， 且主要使用 GRPO（组相对策略优化）而非 PPO。完全开源（权重 + 训练细节）， 在多项推理基准上与 OpenAI o1 持平，是 2025 年最重要的开源 LLM 成果之一。