界面已本地化;技能介绍与说明文档按所选语言由 AI 自动翻译,代码、命令、路径和专业术语保留原文,以原作者文档为准。
探索技能
设计与创意 · SKILL.md

toolprmbench-evaluating-and-advancing-process

toolprmbench-evaluating-and-advancing-process

【设计与创意】Reward-guided search methods have demonstrated strong potential in enhancing tool-using agents by effectively guiding sampling and exploration over complex action spaces. As a core design, those search methods utilize process reward models (PRMs) to provide step-level rewards, enabling more fine-grained monitoring. However, there is a lack of systema…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准

Aadu2021 / skillxivNOASSERTION

技能说明

GitHub
正在从源仓库读取说明…
我的收藏