A dual-model framework that extracts proof sketches from whole-proof candidates and refines them with a tactic model and Sledgehammer, reaching 59.4 percent on miniF2F in Isabelle.
Lego-prover: Neural theorem proving with growing libraries
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.FL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement
A dual-model framework that extracts proof sketches from whole-proof candidates and refines them with a tactic model and Sledgehammer, reaching 59.4 percent on miniF2F in Isabelle.