FareedKhan-dev

FareedKhan-dev/multi-agent-training-grpo

A multi-agent system trained with GRPO for reliable long-horizon task planning and execution.

⭐ 58 ⑂ 11 Jupyter Notebook MIT · 2026-02-09推送
58
Watchers
0
贡献者
0
Commits
0
Releases
0
Open Issues
2026-02-09
最近推送
原文 中文
暂无 README