V
verl-agent
langfengQ/verl-agent
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
★2.2kstars
Python
Apache-2.0
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?Agents project leveraging agent-framework and deepseek-r1, built with Python, open-source
Who made it?Maintained by langfengQ team, 2.2K⭐ on GitHub, #567 out of 2166 in Agents
Why does it exist?In the Agents space, agent-framework workflows faced efficiency bottlenecks. verl-agent was built by langfengQ to address these deepseek-r1 challenges.
What can it do?Key use cases: gigpo, grpo, large-language-models
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/langfengQ/verl-agent | 官网 https://huggingface.co/papers/2505.10978
🔗 github.com/langfengQ/verl-agent | 官网 https://huggingface.co/papers/2505.10978
Topics
agent-frameworkdeepseek-r1gigpogrpolarge-language-modelsllm-agentsllm-trainingreinforcement-learning