A Framework for LLM-based Multi-Agent Reinforced Training and Inference

一颗美丽的圣诞树，由Gemini 3 Pro Preview协作生成，支持手势、鼠标交互，可显示自定义图片及拍立得签名

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"

verl: Volcano Engine Reinforcement Learning for LLMs

🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）

SCoRe: Training Language Models to Self-Correct via Reinforcement Learning

JWT login microservice with plugable backends such as OAuth2, Google, Github, htpasswd, osiam, ..

Implement an advanced backend that efficiently manages JWT-based Access and Refresh Tokens, configures SMTP for sending activation and password reset emails, and enforces single user sessions by lo…

General CNN_Accelerator design.卷积神经网络加速器设计。在PYNQ-Z2 FPGA开发板上实现了卷积池化全连接层等硬件加速计算。

Open-source implementation of AlphaEvolve