WorkForceAgent-R1
Web-task reward functions, WorkArena data processing and GRPO training configurations for reasoning-oriented language agents.
网页
已审阅并标注「强化学习」的研究与资产。
条目依据已审阅标签归类,同一主题不表示资源之间存在依赖关系。日期保留来源精度,注释保留原语言。
Web-task reward functions, WorkArena data processing and GRPO training configurations for reasoning-oriented language agents.
Online RL framework for GUI agents in which VLMs generate the training tasks and judge success from trajectory screenshots, with OSWorld and AndroidLab checkpoints trained from UI-TARS-7B-DPO.
第 241–242 条,共 242 条资源。
通过主题导出清单获取完整记录和证据。克隆目录后,可将主题记录直接交给标准 RAG 与引用导出工具。