awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
RUC-NLPIR avatar

RUC-NLPIR/ARPO

0
View on GitHub↗
1,049 stars·60 forks·Python·15 views

ARPO

[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)

Features

  • Dense Reward Optimization - Agentic reinforcement learning for policy optimization.
  • Policy Optimization - Agentic reinforcement learning for policy optimization.
  • Tool Optimization - Agentic reinforced policy optimization.

Star history

Star history chart for ruc-nlpir/arpoStar history chart for ruc-nlpir/arpo

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Frequently asked questions

What does ruc-nlpir/arpo do?

[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)

What are the main features of ruc-nlpir/arpo?

The main features of ruc-nlpir/arpo are: Dense Reward Optimization, Policy Optimization, Tool Optimization.

Which projects share features with ruc-nlpir/arpo?

Projects with overlapping indexed features include: thudm/treerl — Implementation for ACL'25 paper TreeRL: LLM Reinforcement Learning with On-Policy Tree Search. The implementation is… 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… chanliang/eepo.

Projects sharing features with ARPO

These projects share indexed features with ARPO. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • prime-rl/primePRIME-RL avatar

    PRIME-RL/PRIME

    1,863View on GitHub↗

    ✨ Getting Started • 📖 Introduction 🔧 Usage • 📃 Evaluation • 🎈 Citation • 🌻 Acknowledgement • 📈 Star History

    Python
    View on GitHub↗1,863
  • thudm/treerlTHUDM avatar

    THUDM/TreeRL

    96View on GitHub↗

    Implementation for ACL'25 paper TreeRL: LLM Reinforcement Learning with On-Policy Tree Search. The implementation is based on OpenRLHF

    Python
    View on GitHub↗96
  • multimodal-art-projection/treepomultimodal-art-projection avatar

    multimodal-art-projection/TreePO

    65View on GitHub↗

    This is the official implementation of TreePO algorithm.

    Python
    View on GitHub↗65
  • yangzhch6/treerpoyangzhch6 avatar

    yangzhch6/TreeRPO

    6View on GitHub↗

    ```bash conda create -n rllm python=3.10 -y conda activate rllm

    Jupyter Notebook
    View on GitHub↗6
Compare all 30 related projects
→