Preprint · 2025

REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards

Zafir Stojanovski, Oliver Stanley, Joe Sharratt, Richard Jones, Abdulhakeem Adefioye, Jean Kaddour, Andreas Köpf

Abstract

We introduce Reasoning Gym (RG), a library of reasoning environments for reinforcement learning with verifiable rewards. It provides over 100 data generators and verifiers spanning multiple domains including algebra, arithmetic, computation, cognition, geometry, graph theory, logic, and various common games. Its key innovation is the ability to generate virtually infinite training data with adjustable complexity, unlike most previous reasoning datasets, which are typically fixed. This procedural generation approach allows for continuous evaluation across varying difficulty levels. Our experimental results demonstrate the efficacy of RG in both evaluating and reinforcement learning of reasoning models.

BibTeX Copy

@misc{stojanovski_reasoning_2025,
	title = {{REASONING} {GYM}: {Reasoning} {Environments} for {Reinforcement} {Learning} with {Verifiable} {Rewards}},
	shorttitle = {{REASONING} {GYM}},
	url = {http://arxiv.org/abs/2505.24760},
	doi = {10.48550/arXiv.2505.24760},
	abstract = {We introduce Reasoning Gym (RG), a library of reasoning environments for reinforcement learning with verifiable rewards. It provides over 100 data generators and verifiers spanning multiple domains including algebra, arithmetic, computation, cognition, geometry, graph theory, logic, and various common games. Its key innovation is the ability to generate virtually infinite training data with adjustable complexity, unlike most previous reasoning datasets, which are typically fixed. This procedural generation approach allows for continuous evaluation across varying difficulty levels. Our experimental results demonstrate the efficacy of RG in both evaluating and reinforcement learning of reasoning models.},
	urldate = {2026-11-06},
	publisher = {arXiv},
	author = {Stojanovski, Zafir and Stanley, Oliver and Sharratt, Joe and Jones, Richard and Adefioye, Abdulhakeem and Kaddour, Jean and Köpf, Andreas},
	month = oct,
	year = {2025},
	note = {arXiv:2505.24760 [cs.LG]},
	keywords = {Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Machine Learning},
}