Grpo

AgentGuide is a comprehensive, Chinese-language learning guide and resource aggregator for AI Agent development, targeting career transitions into...

A hands-on curriculum and code repository that teaches modern reinforcement learning from foundational control algorithms through LLM alignment,...

A comprehensive open-source skills library providing 98 structured AI research capabilities across 23 categories (training, evaluation, inference,...

ART is an open-source reinforcement learning framework that trains multi-step LLM-based agents using GRPO, enabling models like Qwen, Llama, and...

This repository is the official code companion to a Manning book that teaches how to build a reasoning LLM from scratch using PyTorch, starting with...

ms-swift is a comprehensive fine-tuning and deployment framework for 600+ large language models and 300+ multimodal models, supporting training...

OpenClaw-RL is a reinforcement learning framework that enables training personalized agents through natural language interaction, supporting...

Judgeval is an open-source Python SDK for agent monitoring and continuous improvement that provides OpenTelemetry-based tracing, agent-judge...

VLM-R1 is a specialized research framework for training vision-language models using reinforcement learning (R1-style approach and GRPO), built on...

MixGRPO is a research project that combines flow-based models with mixed ODE-SDE approaches to improve the efficiency of GRPO (Generative Reward...

Skywork-R1V is a series of advanced multimodal reasoning models that combine vision and language understanding with chain-of-thought capabilities,...