Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information
Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models. Yet, typical RLVR approaches fail on difficult problems: when a model cannot generate any correct solutions, it receives \textit{zero} learning signal. Providing privileged guidance during training, such as solution prefixes, can help overcome this learning cliff by steering the model towards {correct solutions with non-zero reward}. {We call these rollouts \textit{off-context}: they are generated from a training prompt that contains privileged guidance, while the target objective is defined by t
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.
- FuzzyOverlapping authors or contributors · 62%affaan-m/ECC →
“Shared author/contributor keys: jiang”
- FuzzyOverlapping authors or contributors · 62%BerriAI/litellm →
“Shared author/contributor keys: jiang”
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “Off-Context GRPO: Learning to Reason on Hard Problems using ” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Priyank Agrawal →
“Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information”
- LinkedLinked via arxiv author · 85%Ankur Samanta →
“Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information”
- LinkedLinked via arxiv author · 85%Shervin Ghasemlou →
“Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information”
- LinkedLinked via arxiv author · 85%Jalaj Bhandari →
“Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information”
- LinkedLinked via arxiv author · 85%Kavosh Asadi →
“Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information”