Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning

Jul 15, 2026

A new preprint introduces Ring-Zero, a training pipeline that successfully scales reinforcement learning with verifiable rewards (zero RL) to a 1-trillion-parameter model. The authors report that scaling leads to significant improvements in sample efficiency and performance, and that the model exhibits emergent advanced reasoning behaviors such as self-verification and parallel reasoning. On seven mathematical benchmarks, the model achieves competitive results and demonstrates advantages in producing structured and concise reasoning traces.

Why it matters: This work provides evidence that scaling zero RL to trillion-parameter models can yield emergent reasoning capabilities, offering new insights into the development of large-scale reasoning systems.

Full story at: arXiv Computation and Language ↗