PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
In long-horizon LLM agent reinforcement learning, weak policies often repeat similar failures, producing uninformative rollout trajectories and limiting effective policy optimization. Existing skill-centric methods improve exploration by optimizing, filtering, or internalizing reusable skills. However, they remain centered on the skills themselves rather than being designed as adaptive training-time support for the evolving policy. To address this, we propose a policy-centric training paradigm that reframes skills as a dynamic training scaffold. Our framework, Pats, converts rollout groups fro
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%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzySimilar title/name (fuzzy) · 59%Fosowl/agenticSeek →
“Fuzzy title match (0.73): “PATS: Policy-Aware Training Scaffolding for Agentic Reinforc” ≈ “Fosowl/agenticSeek””
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “PATS: Policy-Aware Training Scaffolding for Agentic Reinforc” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Yipeng Shi →
“PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning”
- LinkedLinked via arxiv author · 85%Zhipeng Ma →
“PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning”
- LinkedLinked via arxiv author · 85%Tengyue Wang →
“PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning”
- LinkedLinked via arxiv author · 85%Qitai Tan →
“PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning”