We explore if RL can be useful for symbolic mathematics. Previous work showed contrastive learning can solve linear equations in one variable. We show model-free PPO \cite{schulman2017proximal} augmented with curiosity-based exploration and graph-based actions can solve nonlinear equations such as those involving radicals, exponentials, and trig functions. Our work suggests curiosity-based exploration may be useful for general symbolic reasoning tasks.
Cite
@article{arxiv.2510.17022,
title = {Curiosity-driven RL for symbolic equation solving},
author = {Kevin P. O'Keeffe},
journal= {arXiv preprint arXiv:2510.17022},
year = {2025}
}