Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning
EAPO uses policy entropy to reinforce surprising successes and penalize repeated failures in LLM reasoning.
1 stories, newest first · one card per story
EAPO uses policy entropy to reinforce surprising successes and penalize repeated failures in LLM reasoning.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views