verl-agent - a langfeng01 Collection

langfeng01 's Collections

verl-agent

updated Mar 2

Open-source models trained via GiGPO and verl-agent

langfeng01/GiGPO-Qwen2.5-7B-Instruct-WebShop

8B • Updated Sep 28, 2025 • 363
langfeng01/GiGPO-Qwen2.5-7B-Instruct-ALFWorld

8B • Updated Sep 28, 2025 • 947 • 1
Group-in-Group Policy Optimization for LLM Agent Training

Paper • 2505.10978 • Published May 16, 2025 • 23