DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
논문 링크 Subgoal Curriculum + CoT Consistency: DeepSeek-Prover-V2가 자동 정리 증명의 판을 갈아엎다 TL;DR DeepSeek-Prover-V2는 **“문제를 잘게 쪼개고, 쪼갠 대로 끝까지 맞춘다”** …
23 분
2504.21801v1
formal-theorem-proving
automated-reasoning
math-llm
chain-of-thought
proof-verification
formal-mathematics
DeepSeek