Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks
英文标题：Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks
arXiv:2607.22724v1 Announce Type: new Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing trajectories or steps within a group. However, on difficult long-horizon tasks, this comparison can suffer f
打开原文相关 3.2 · 机会 1
2.1 KB
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2607.22724v1 Announce Type: new Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing trajectories or steps within a group. However, on difficult long-horizon tasks, this comparison can suffer f
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×