1
Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Training
强化学习训练智能体搜索时，巧妙回收零方差查询，效率提升有新思路。
arXiv:2606.10709v1 Announce Type: cross Abstract: The use of GRPO-style algorithms has become the standard strategy for training LLM search agents und…