Using Pass@k as an RLVR reward, with bootstrap sampling and an analytical advantage formula, improves exploration and later Pass@1 performance of reasoning LLMs.
Aime2024, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
Using Pass@k as an RLVR reward, with bootstrap sampling and an analytical advantage formula, improves exploration and later Pass@1 performance of reasoning LLMs.