大模型推理能力

RLMEval: Evaluating Research-Level Neural Theorem Proving

Auguste Poiroux, Antoine Bosselut, Viktor Kunčak

专题命中 代码与定理证明 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted to EMNLP 2025 Findings. RLMEval benchmark released: https://github.com/augustepoiroux/RLMEval