DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning

Journal:

Nature

Published:

2025-09-17

DOI:

10.1038/s41586-025-09422-z

Affiliations:

7

Authors:

194

Go to article

Institutions	Authors	Share
DeepSeek, China	194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000 194.000000	1.00

Interested in Machine Learning?