ReverseMath: Answer Inversion for Scalable and Verifiable Mathematical Problem Generation

arXiv:2605.27709v1 Announce Type: new Abstract: Mathematical reasoning benchmarks are vital for evaluating large language models (LLMs), but many are static and repeatedly exposed through public evaluation and training pipelines, making it difficult to separate genuine reasoning from memorization. Meanwhile, manually constructing new math problems with reliable answers remains costly. We introduce ReverseMath, a scalable method for generating new math problems through answer inversion. Given a