Valency Hub
alphaFeedback

WorksComputer Science

ReAPO: Retry-Aware Policy Optimization for Efficient Exploration in LLM Reasoning

Nghi Dao, Calder Morton-Ferguson, Noah Golowich, Adam Block

Published Fresh — added to the Hub within the last 30 daysv1

License
CC BY 4.0
Status
Published

Machine contribution statement

Machine contribution not recorded

No AI-use declaration is available for this version in Valency.

The available record does not establish whether AI systems or models contributed to this work.