arXiv Machine Learning
LeanPolish: Verified Supervision for Lean Proof Compression
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 15
LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification
arXiv:2610.17697v1 Announce Type: cross Abstract: AI systems now write long and difficult mathematical proofs, and checking their step-by-step validity is becoming a bottleneck. A learned verifier co...
arXiv AI
Sep 2
RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving
RePro is a framework that rewrites benchmark problems for large language models (LLMs) in mathematical problem solving, ensuring that the rewritten problems and their answers are valid and correct through Lean-verified proofs. It integrates Lean-oriented neural automated theorem provers (ATPs) to regenerate answers, achieving 100% well-definedness, feasibility, and answer correctness on GSM8K and MATH datasets. Experiments show that models’ performance drops on these proof‑verified rewritten benchmarks, indicating sensitivity to surface‑level and structural variations and potential memorization effects.
arXiv Machine Learning
Oct 16
Learning Lean Feedback for Efficient Proof-Candidate Evaluation on GPUs
The paper presents a neural evaluator that predicts Lean 4 theorem‑proving verdicts and compiler feedback, trained on 4.84 million labelled programs. A two‑stage approach—first screening candidates with a validity classifier, then scoring positives with a feedback model—achieves 87.8 % accuracy on a 68,932‑program benchmark and processes 3.5 candidates per second on an H100 GPU, outperforming a 64‑worker Lean baseline. Integrating this evaluator into a hybrid reward system reduces GRPO training steps by about 31 % while maintaining comparable miniF2F pass rates.
arXiv AI
Jun 12
Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation
arXiv:2606. 12594v1 Announce Type: new Abstract: Modern Lean theorem provers achieve strong performance only with substantial training and inference compute, driven in part by scarce verified proof data and the long reasoning traces of formal proof search, making both supervised fine-tuning (SFT) and sampling expensive.
arXiv AI
Jun 19
Process-Verified Reinforcement Learning for Theorem Proving via Lean
arXiv:2606. 20068v1 Announce Type: new Abstract: While reinforcement learning from verifiable rewards (RLVR) typically has relied on a single binary verification signal, symbolic proof assistants in formal reasoning offer rich, fine-grained structured feedback.
arXiv AI
Sep 1
Reward-Oracle MCTS for Formal Theorem Proving: Sample-Efficient Search and the Need for Kernel-Level Proof Auditing
arXiv:2608.28639v1 Announce Type: new Abstract: Formal theorem proving with large language models remains challenging due to the difficulty of navigating large proof search spaces efficiently. Existi...