ReAPO: Retry-Aware Policy Optimization for Efficient Exploration in LLM Reasoning
arXiv:2610.28770v1 Announce Type: new Abstract: RLVR improves language-model reasoning, but commonly relies on independent stochastic rollouts for exploration, which can repeatedly sample similar failed strategies. Prior work has seen success with approaches that guide exploration by introducing de…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-22 04:00 · arXiv cs.LG
ReAPO: Retry-Aware Policy Optimization for Efficient Exploration in LLM Reasoning