DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
Paper Subgoal Curriculum + CoT Consistency: DeepSeek-Prover-V2 Reshapes Automated Theorem ProvingTL;DRDeepSeek-Prover-V2, built on the …
26 min
math-llm
Chain-of-Thought
proof-verification
formal-mathematics
DeepSeek