DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition

Tue, 08 Jul 2025 00:00:00 +0900

Paper

Subgoal Curriculum + CoT Consistency: DeepSeek-Prover-V2 Reshapes Automated Theorem Proving

TL;DR

DeepSeek-Prover-V2, built on the principle of “breaking a problem into small pieces and then matching them all the way through,” achieves a new SOTA on MiniF2F Pass@32 of 82.4% (671B) and 75.6% (7B) even in a small 7B model. The key is the combination of Subgoal-guided Curriculum and Chain-of-Thought-Lean consistency reward (GRPO).

Math-Llm on Jaehun's Blog

DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition

Subgoal Curriculum + CoT Consistency: DeepSeek-Prover-V2 Reshapes Automated Theorem Proving

TL;DR