← Back to all news
arXiv Machine Learning By Lazar Milikic, Etienne Bamas, Emmanuel Abbe, Viktor Kun\v{c}ak

Learning Lean Feedback for Efficient Proof-Candidate Evaluation on GPUs

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 21

BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models

BoostAPR is a three-stage framework that improves automated program repair by using execution-grounded reinforcement learning with dual reward models. The approach first fine‑tunes a model on execution‑verified demonstrations, then trains a sequence‑level assessor and a line‑level credit allocator from execution outcomes, and finally applies PPO optimization where the line‑level model redistributes rewards to critical edit regions. Evaluated on SWE‑Gym and four benchmarks, BoostAPR achieves significant gains, including 40.7% on SWE‑bench Verified and 95.0% on QuixBugs, demonstrating strong cross‑language generalization.

By Yuanhao Li, Hongbo Wang, Xiaotang Shang, Xunzhu Tang, Yiming Cao, Xuhong Chen
reinforcement-learningfine-tuningbenchmarks
More like this →
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.

By Xiyuan Zhou, Zhuoqi Li, Xinlei Wang, Yirui He, Yuhao Wu, Yuheng Cheng, Yan Xu, Junhua Zhao, Jinjin Gu
llmsbenchmarks
More like this →