LLMs in a conjecturing-proving loop that conditions on their own prior verified Lean proofs discover more hard-to-prove theorems than baselines that generate statements and proofs together.
On some classes of nearly open sets.Pacific journal of mathematics, 15(3):961–970, 1965
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Discovering New Theorems via LLMs with In-Context Proof Learning in Lean
LLMs in a conjecturing-proving loop that conditions on their own prior verified Lean proofs discover more hard-to-prove theorems than baselines that generate statements and proofs together.