credit assignment
2 stories tagged “credit assignment”.
-
Moving Beyond Timestamps: On-Policy Distillation Aligned with Decisions for Long-Horizon Agents
AlignOPSD moves distillation from timestamps to functional decision spans, using credit assignment to improve …
Oct 17, 2026Research -
Unexpected Success, Persistent Failure: Entropy-Driven Credit Assignment for Exploration in LLM Reasoning
EAPO uses entropy to assign token credit in LLM reasoning, penalizing confident failures, rewarding uncertain …
Oct 14, 2026Research