SAT-RL: Training Language Models for Logical Reasoning with Symbolic Solvers
arXiv:2610.14402v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance in mathematical and logical reasoning, yet they still suffer from the curse of complexity and struggle as problem difficulty...
Read more: https://arxiv.org/abs/2610.14402
Scan with your phone
Scan with your phone