flâneur

DeepSeek-R1

arxiv.org · 34,661 words · saved by 14 readers

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.

# link_1fwbzg55bq2.pdf ## Metadata - PDFFormatVersion=1.7 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - Author=DeepSeek-AI; Daya Guo; Dejian Yang; Haowei Zhang; Junxiao Song; Peiyi Wang; Qihao Zhu; Runxin Xu; Ruoyu Zhang; Shirong Ma; Xiao Bi; Xiaokang Zhang; Xingkai Yu; Yu Wu; Z. F. Wu; Zhibin Gou; Zhihong Shao; Zhuoshu Li; Ziyi Gao; Aixin Liu; Bing Xue; Bingxuan Wang; Bochao Wu; Bei Feng; Chengda Lu; Chenggang Zhao; Chengqi Deng; Chenyu Zhang; Chong Ruan; Damai Dai; Deli Chen; Dongjie Ji; Erhang Li; Fangyun Lin; F

saved by

related reading