learn.ifs.name

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

DeepSeek-AI, 2025, DeepSeek-R1 (arXiv preprint arXiv:2501.12948)

Subscriber deck — free during early access

1 cards in “1 Introduction” · whole deck

1 Introduction

  1. What question does the DeepSeek-R1 report set out to answer?
    Whether an LLM can develop strong reasoning through reinforcement learning alone, without supervised examples of reasoning. o1 had shown that longer chains of thought at inference help, but not openly how to train for them.
    • DeepSeek-AI, 2025, DeepSeek-R1 (arXiv preprint arXiv:2501.12948), §1

Source

  • DeepSeek-AI. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. In arXiv preprint arXiv:2501.12948. https://arxiv.org/abs/2501.12948