Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
Reinforcement learning with verifiable rewards without human-annotated data, often referred to as zero RL, has emerged as a powerful paradigm for eliciting chain-of-thought reasoning. However, due to computational constraints, existing studies are largely restricted to small models, leaving the training dynamics and emergent capabilities at a large scale unexplored. To meaningfully explore this frontier, we aim to elicit high-quality reasoning behaviors from the model. However, we find that naive scaling often suffers from poor readability, token redundancy, and a lack of adaptive reasoning de
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 53%sileod/reasoning-core →
- PossiblePossibly related (embedding) · 52%rllm-org/rllm →
- PossiblePossibly related (embedding) · 51%pytorch/rl →
- PossiblePossibly related (embedding) · 51%hscspring/rl-llm-nlp →
- PossiblePossibly related (embedding) · 50%Northwind AI →
- LinkedLinked via arxiv author · 85%Xinyu Tang →
“Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning”
- LinkedLinked via arxiv author · 85%Gangqiang Cao →
“Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning”
- LinkedLinked via arxiv author · 85%Yurou Liu →
“Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning”