grpo

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

Implement a reasoning LLM in PyTorch from scratch, step by step

OpenClaw-RL: Train any agent simply by talking

Solve Visual Understanding with Reinforced VLMs

🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

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"

Multimodal RL training framework for diffusion & omni models

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

A systematic AI Agent development tutorial covering LLM agents, RAG, tool use, memory systems, multi-agent systems, LangChain, LangGraph, MCP, and agentic RL.｜从零开始学 AI Agent 开发 | 系统、全面、实战导向的 Agent 开发教程 | 每日自动追踪 arXiv 最新论文 | Learn AI Agent Development from Scratch

RL environments + evals for AI agents. Define once, train anything.

🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

The open source implementation of DeepSeek-R1. 开源复现 DeepSeek-R1

BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model | NeurIPS '25