How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
✨ Getting Started • 📖 Introduction 🔧 Usage • 📃 Evaluation • 🎈 Citation • 🌻 Acknowledgement • 📈 Star History
ICLR 2026 Agentic Reinforced Policy Optimization (ARPO)
This is the official implementation of TreePO algorithm.
```bash conda create -n rllm python=3.10 -y conda activate rllm
Implementation for ACL'25 paper TreeRL: LLM Reinforcement Learning with On-Policy Tree Search. The implementation is based on OpenRLHF
The main features of thudm/treerl are: Dense Reward Optimization, Policy Optimization.
Open-source alternatives to thudm/treerl include: ruc-nlpir/arpo — [ICLR 2026] Agentic Reinforced Policy Optimization (ARPO). yangzhch6/treerpo — ```bash conda create -n rllm python=3.10 -y conda activate rllm. multimodal-art-projection/treepo — This is the official implementation of TreePO algorithm. prime-rl/prime — ✨ Getting Started • 📖 Introduction 🔧 Usage • 📃 Evaluation • 🎈 Citation • 🌻 Acknowledgement • 📈 Star History. trademaster-ntu/trademaster — TradeMaster is a reinforcement learning trading framework and algorithmic trading simulator designed for designing and… chenxinan-fdu/polaris — 🌠 A PO st-training recipe for scaling R L on A dvanced R eason I ng model S 🚀.