Get Started
Home
Topics
Search
Library
Research questionHow can automated Lean 4 proof search reuse promising partial proofs without later revisions degrading them?In real-world Lean projects, proof attempts may contain useful partial progress even when they fail to compile. Continuing the wrong attempt can discard that progress, while exploring too many alternatives wastes inference calls.
AI
Code Generation & Program Synthesis
Evaluation & Benchmarks
Reasoning
Research Paper
Technology
Latest papersRecent research connected to this question, newest first.Compiler-Guided Adaptive Proof Search with Cross-Model Synergy on Context-Dependent Theorem ProvingThe source concerns compiler-guided, iterative proof search using language-model-generated Lean 4 proofs and compiler feedback. Its evidence covers seven real-world projects from miniCTX-v2 and reports effectiveness and LLM-call efficiency within a pass@32 budget; broader generalization is not established.research paper · Sep 4, 2026
Related questions
How can autoformalization preserve diverse faithful statements that improve prover search under a fixed budget?How can LLM prompts be automatically refined from recurring reasoning errors without laborious manual engineering?How can large reasoning models explore complex research problems while maintaining proof rigor?How can we detect when a compiling Lean formalization changes the intended natural-language meaning?