DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learningDaya Guo, Junlong Li, Runxin Xu et al.|Nature|2025Cited by 610
Can Open Large Language Models Catch Vulnerabilities?DeepSeek-AI, Haowei Zhang, Daya Guo et al.|arXiv (Cornell University)|2025Cited by 501
DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal DecompositionZ. Z. Ren, Chong Ruan, Zhihong Shao et al.|arXiv (Cornell University)|2025Cited by 0