PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs
Reinforcement learning (RL) is used to improve the reasoning abilities of LLMs, while training data span heterogeneous tasks. However, most RL post-training pipelines rely on fixed or manually designed task mixtures, even though task usefulness changes as training progresses. Online curriculum methods often define learnability by update magnitude, ignoring whether the update translates into reward gains, which can misallocate rollout budget toward tasks with large but ineffective updates. We propose PAC, a Progress-Augmented Advantage Curriculum for multi-task RL of LLMs that combines two task
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%modular/modular →
“Shared author/contributor keys: liu”
- LinkedLinked via arxiv author · 85%Yuanqiang Yu →
“PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs”
- LinkedLinked via arxiv author · 85%Yanzhao Zheng →
“PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs”
- LinkedLinked via arxiv author · 85%Zhentao Zhang →
“PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs”
- LinkedLinked via arxiv author · 85%Tianze Xu →
“PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs”
- LinkedLinked via arxiv author · 85%Chao Ma →
“PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs”
- LinkedLinked via arxiv author · 85%Jihuai Zhu →
“PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs”
- LinkedLinked via arxiv author · 85%Jiashun Liu →
“PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs”