An online pre-rollout filter that predicts and skips zero-variance prompts from reward dynamics reduces GRPO rollout time by up to 2.4x with comparable math reasoning accuracy.
Data-efficient finetuning using cross-task nearest neighbors
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
An online pre-rollout filter that predicts and skips zero-variance prompts from reward dynamics reduces GRPO rollout time by up to 2.4x with comparable math reasoning accuracy.