SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating 文章

ArXiv CS.AI2026-06-08NEWSen作者: Zequn Xie, Junjie Wang, Dan Yang, Jie Feng, Yue Shen, Jian Wang, Jinjie Gu

SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating · 相关技术

相关技术