The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models

Excerpt

arXiv:2610.02191v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical problems, it remains unclear whether they possess the structural mathematical understanding underlying their solutions. In this paper, we take a first step toward systematically studying mathematical understanding in LLMs, from diagnosing its distinct capabilities to leveraging these findings to improve post-training. First, we introduce the notion o