DeepSeek-Prover-V2: recursively building Lean-checked proof-search training

What changed

DeepSeek-Prover-V2 used recursive subgoal decomposition and Lean-checked training traces for formal proof search, reporting 217/244 miniF2F test problems at 8192 samples and 47 PutnamBench problems in the selected corrected v2 evaluation.

Scientific scope

DeepSeek-Prover-V2 used recursive subgoal decomposition and Lean-checked training traces for formal proof search, reporting 217/244 miniF2F test problems at 8192 samples and 47 PutnamBench problems in the selected corrected v2 evaluation. The target is arXiv 2504.21801v2. Lean proof search is evaluated on specified formal statements and sampling budgets; it does not establish autonomous resolution of an unrelated open mathematical problem. The final Putnam result retains 47 accepted problems after two misformalizations were removed from the earlier 49. The 649 compatible problems used in the filtered dataset differ from the advertised 658. MiniF2F and FormalAIME results have separate denominators and budgets; supplied answers in FormalAIME matter. The paper discloses a Lean 4.9 release-candidate bug affecting the 7B experiment. Statement vacuity and kernel/environment correctness must be checked separately. WRS has not independently rerun the benchmarks.

Evidence

Source-linked, scoped account of the original work. The published scope states the scientific assumptions and remaining verification limits. WRS has not independently certified the full proof, experimental result or system benchmark.

Contributors

• Source-listed research team (full original byline retained in record) · SCIENCE: Scientific system design, training, experiments and paper; no individual effort fractions inferred.
• DeepSeek-Prover-V2 / DeepSeek-V3 · EXECUTION: Source-reported automated mathematical execution within the stated benchmark and sampling scope; not a human author or independent WRS audit.

• Ren et al., Deep Seek-Prover-V 2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition — ar Xiv 2504.21801 v 2

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction