30 open-source projects similar to aiframeresearch/spo, ranked by how many features they have in common. Compare stars, activity and what each one does to find the best AIFrameResearch SPO alternative.
This project is a collection of PyTorch learning resources and educational guides designed to teach the construction and training of neural networks. It serves as a comprehensive deep learning tutorial covering various model architectures and practical implementation strategies. The resources provide specific guidance on implementing computer vision tasks, such as image classification and synthetic imagery generation, as well as reinforcement learning agents using value networks and experience replay. It also covers sequential data modeling through recurrent networks and generative modeling u
RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface
The code for BRIDGE (Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning).
2025/10/23 🔥🔥Our paper is accepted by NeurIPS 2025.🔥🔥 - 2025/04/22 Released our Paper on arXiv. See here - 2025/03/24 We re-implement our algorithm based on verl. ✨✨ Key features: (1) add ~50 additional metrics to comprehensively monitor the training process and stability, (2) add a…
This repository contains the code for our paper titled "Optimizing Test-Time Compute via Meta Reinforcement Finetuning." In this work, we introduce a novel approach to optimizing test-time compute through meta reinforcement learning, aiming to balance the efficiency and discovery capabilities of…
🔧✨Tool-Star: Empowering Multi-Tool Collaborative Web Agent via Reinforcement Learning
LUFFY: Learning to Reason Under Off‑Policy Guidance A general framework for off-policy learning in large reasoning models.
Princeton University \& PKU \& UIUC \& University of Chicago \& ByteDance Seed
December 5, 2025 🔍 We propose entropy ratio clipping (ERC) to impose a global constraint on the output distribution of the policy model. Experiments demonstrate that ERC can significantly improve the stability of off-policy training. 📄 The paper is available on arXiv.
Paper - Abstract - Updates - Quick Start - Installation - Download the datasets - Create Experiment Script - Single GPU Training (Only for Rho models) - Running the experiments - Code Structure - Initial SFT Checkpoints - Acknowledgement - Citation
Open-source / Comprehensive / Lightweight / Easy-to-use
Minzheng Wang 1,2 , Yongbin Li 3 , Haobo Wang 4 , Xinghua Zhang 3🌟 , Nan Xu 1 , Bingli Wu 3 , Fei Huang 3 , Haiyang Yu 3 , Wenji Mao 1,2🌟
This is the official implementation of TreePO algorithm.
This repository accompanies the paper Let's Verify Step by Step and presents the PRM800K dataset introduced there. PRM800K is a process supervision dataset containing 800,000 step-level correctness labels for model-generated solutions to problems from the MATH dataset. More information on…
✨ Getting Started • 📖 Introduction 🔧 Usage • 📃 Evaluation • 🎈 Citation • 🌻 Acknowledgement • 📈 Star History
ICLR 2026 Agentic Reinforced Policy Optimization (ARPO)
👋 Hi, everyone! verl is a RL training library initiated by ByteDance Seed team and maintained by the verl community.
Implementation for ACL'25 paper TreeRL: LLM Reinforcement Learning with On-Policy Tree Search. The implementation is based on OpenRLHF
This repository contains the code for the paper "Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process".
```bash conda create -n rllm python=3.10 -y conda activate rllm
👋 Hi, everyone! verl is a RL training library initiated by ByteDance Seed team and maintained by the verl community.
Yizhou Zhou*   Zhou Ziheng   Yingzhe Peng   Xinyu Ye   Xinting Hu   Wenbo Zhu   Lu Qi   Ming-Hsuan Yang   Xu Yang  
StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization