English

Curiosity-driven RL for symbolic equation solving

Machine Learning 2025-10-30 v2 Artificial Intelligence

Abstract

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}
}

Comments

Accepted at the NeurIPS 2025 MATH-AI Workshop

R2 v1 2026-07-01T06:46:12.199Z