A self-play loop in which an LLM generates conjectures graded by its own prover's pass rate doubles the LeanWorkbook solve rate to 28.5% and sets whole-proof-method records on miniF2F (65.0% pass@3200), ProofNet (23.9%), and PutnamBench (8/644).
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
A self-play loop in which an LLM generates conjectures graded by its own prover's pass rate doubles the LeanWorkbook solve rate to 28.5% and sets whole-proof-method records on miniF2F (65.0% pass@3200), ProofNet (23.9%), and PutnamBench (8/644).