Learning to Reason Efficiently with A* Post-Training 事件

Learning to Reason Efficiently with A* Post-Training arXiv:2605.24597v1 Announce Type: cross Abstract: Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid proof itself, requiring a reasoning procedure in which intermediate inferences are correct. Specifically, we investigate whether LLMs can learn to generate