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

We present Ring-Zero, a stable training pipeline scaling Zero RL to one trillion parameters. Our experiments reveal that massive scaling enhances sample efficiency and triggers spontaneous cognitive behaviors like self-verification and parallel reasoning. These emergent capabilities render hand-crafted heuristics redundant, proving that size alone drives advanced chain-of-thought reasoning without human-annotated data.

"The model spontaneously develops advanced cognitive behaviors, including anthropomorphism, structured formatting, self-verification, parallel reasoning, and context anxiety, rendering hand-crafted heuristics redundant."