English

CircuitBuilder: From Polynomials to Circuits via Reinforcement Learning

Machine Learning 2026-03-19 v1 Artificial Intelligence Computational Complexity

Abstract

Motivated by auto-proof generation and Valiant's VP vs. VNP conjecture, we study the problem of discovering efficient arithmetic circuits to compute polynomials, using addition and multiplication gates. We formulate this problem as a single-player game, where an RL agent attempts to build the circuit within a fixed number of operations. We implement an AlphaZero-style training loop and compare two approaches: Proximal Policy Optimization with Monte Carlo Tree Search (PPO+MCTS) and Soft Actor-Critic (SAC). SAC achieves the highest success rates on two-variable targets, while PPO+MCTS scales to three variables and demonstrates steady improvement on harder instances. These results suggest that polynomial circuit synthesis is a compact, verifiable setting for studying self-improving search policies.

Cite

@article{arxiv.2603.17075,
  title  = {CircuitBuilder: From Polynomials to Circuits via Reinforcement Learning},
  author = {Weikun K. Zhang and Rohan Pandey and Bhaumik Mehta and Kaijie Jin and Naomi Morato and Archit Ganapule and Michael Ruofan Zeng and Jarod Alper},
  journal= {arXiv preprint arXiv:2603.17075},
  year   = {2026}
}

Comments

ICLR 2026 Workshop on AI with Recursive Self-Improvement

R2 v1 2026-07-01T11:25:04.071Z