Get the latest tech news
DeepSeek-Prover-V2
Contribute to deepseek-ai/DeepSeek-Prover-V2 development by creating an account on GitHub.
To construct the cold-start dataset, we develop a simple yet effective pipeline for recursive theorem proving, utilizing DeepSeek-V3 as a unified tool for both subgoal decomposition and formalization. Once the decomposed steps of a challenging problem are resolved, we pair the complete step-by-step formal proof with the corresponding chain-of-thought from DeepSeek-V3 to create cold-start reasoning data. After fine-tuning the prover model on the synthetic cold-start data, we perform a reinforcement learning stage to further enhance its ability to bridge informal reasoning with formal proof construction.
Or read this on Hacker News