[2501.12948] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Abstract:General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-thought prompting, have achieved considerable success on foundational reasoning tasks. However, this success is heavily contingent upon extensive human-annotated demonstrations, and models' capabilities are still insufficient for more complex problems. Here we show that the reasoning abilities of LLMs can be incentivized through pure reinforcement learning (RL), obviating the need for human-labeled reasoning trajectories. The proposed RL framework facilitates the emergent development of advanced reasoning patterns, such as self-reflection, verification, and dynamic strategy adaptation. Consequently, the trained model achieves superior performance on verifiable tasks such as mathematics, coding competitions, and STEM fields, surpassing its counterparts trained via conventional supervised learning on human demonstrations. Moreover, the emergent reasoning patterns exhibited by these large-scale models can be systematically harnessed to guide and enhance the reasoning capabilities of smaller models.

[2501.12948] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2501.12948 (cs) [Submitted on 22 Jan 2025 ( v1 ), last revised 4 Jan 2026 (this version, v2)] Title: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning Authors: DeepSeek-AI , Daya Guo , Dejian Yang , Haowei Zhang , Junxiao Song , Peiyi Wang , Qihao Zhu , Runxin Xu , Ruoyu Zhang

related reading

• DeepSeek-R1arxiv.org
• [2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• [2504.13837] Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?arxiv.org
• [2606.10346] Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learningarxiv.org
• [2412.14135] Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspectivearxiv.org
• DeepSeek Proves AI Comes for All Jobs - Even AI Jobssubstack.com
• The State of Reinforcement Learning for LLM Reasoningmagazine.sebastianraschka.com
• Reasoning Models Reason Well, Until They Don'tarxiv.org
• DeepSeek R1's recipe to replicate o1 and the future of reasoning LMsinterconnects.ai
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelsarxiv.org