标签：GRPO

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).

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.

AI Agent 开发指南 | Agent Harness | 上下文工程 | 高级 RAG | MCP | Agentic RL 强化学习 | LangGraph 实战 | 1.2 万+ 大模型面试题 | 算法岗 / 开发岗求职 | 转行大模型

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!

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

Solve Visual Understanding with Reinforced VLMs

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

Multimodal RL training framework for diffusion & omni models

Halo is an open-source framework built by White Circle for training large language and multimodal models

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

LightRFT: Light, Efficient, Omni-modal & Reward-model Driven Reinforcement Fine-Tuning Framework

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

Your AI intranet: network the computers you already own for inference and training.

[ICML-2026] Official implementation of "SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience"

🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models

[ICLR 2026] An official implementation of "CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning"