1
Evaluating Research-Level Math Proofs via Strict Step-Level Verification
研究指出大语言模型在严格验证复杂数学证明上的缺陷，提出逐步验证新范式。
arXiv:2606.10799v1 Announce Type: new Abstract: Large Language Models (LLMs) struggle to rigorously verify complex mathematical proofs. Standard globa…