1
CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged Feedback
提出信用衰减特权反馈方法，引导搜索代理在硬问题上突破成功轨迹稀疏瓶颈
arXiv:2606.01830v1 Announce Type: new Abstract: Recent LLM search agents use reinforcement learning with verifiable rewards (RLVR) to learn search-aug…