Kimina-Prover：在大型形式化推理模型中應用測試時強化學習搜尋 (Test-time RL Search)★ 82
Hugging Face Blog·339 days ago·Release
Hugging Face's AI-MO (AI Math Olympiad) team has officially published Kimina-Prover, a research paper demonstrating how "test-time reinforcement learning…
