Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization
Outcome-based reinforcement learning provides verified feedback for language-model agents, but assigns trajectory-level advantage uniformly to all decisions, yielding coarse credit over long-horizon interactions. On-policy self-distillation offers finer supervision by re-evaluating sampled behavior with privileged information (PI) available only during training. However, fine-grained supervision is not necessarily fine-grained credit: PI-induced likelihood changes describe how additional information alters policy preference, but do not directly determine how an executable action should inherit
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.
- FuzzySimilar title/name (fuzzy) · 84%roboflow/supervision →
“Fuzzy title match (0.92): “Reconciling Process Supervision with Outcome-Based Credit in” ≈ “roboflow/supervision””
- FuzzyOverlapping authors or contributors · 62%langchain-ai/langchain →
“Shared author/contributor keys: gan”
- FuzzySimilar title/name (fuzzy) · 59%WenyuChiou/awesome-agentic-ai-zh →
“Fuzzy title match (0.73): “Reconciling Process Supervision with Outcome-Based Credit in” ≈ “WenyuChiou/awesome-agentic-ai-zh””
- FuzzySimilar title/name (fuzzy) · 59%Fosowl/agenticSeek →
“Fuzzy title match (0.73): “Reconciling Process Supervision with Outcome-Based Credit in” ≈ “Fosowl/agenticSeek””
- LinkedLinked via arxiv author · 85%Jingxiao Yang →
“Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization”
- LinkedLinked via arxiv author · 85%Wangjie Gan →
“Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization”
- LinkedLinked via arxiv author · 85%Yingxuan Zhuang →
“Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization”
- LinkedLinked via arxiv author · 85%Wenqi Zhang →
“Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization”