pith. sign in

2505.17218 , archivePrefix=

Effective Reinforcement Learning for Reasoning in Language Models , author= · arXiv 2505.17218

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

clear filters

representative citing papers

PS-PPO: Prefix-Sampling PPO for Critic-Free RLHF

cs.LG · 2026-06-29 · unverdicted · novelty 6.0

PS-PPO samples prefixes of trajectories in critic-free RLHF and uses importance-weighted updates to reduce compute and memory while claiming to preserve the full-trajectory objective.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • PS-PPO: Prefix-Sampling PPO for Critic-Free RLHF cs.LG · 2026-06-29 · unverdicted · none · ref 21

    PS-PPO samples prefixes of trajectories in critic-free RLHF and uses importance-weighted updates to reduce compute and memory while claiming to preserve the full-trajectory objective.