Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
| Date | Stars |
|---|---|
| 2026-07-31 | 1849 |
| 2026-08-02 | 1848 |
| 2026-08-06 | 1848 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome-AgenticLLM-RL-Papers
This is the Official repo for the survey paper: The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
[ArXiv – https://arxiv.org/abs/2509.02547](https://arxiv.org/abs/2509.02547)
[HuggingFace – https://huggingface.co/papers/2509.02547](https://huggingface.co/papers/2509.02547)
## Citation
```bibtex
@article{
zhang2026landscapeagenticreinforcementlearning,
title={The Landscape of Agentic Reinforcement Learning for {LLM}s: A Survey},
author={Guibin Zhang and Hejia Geng and Xiaohang Yu and Zhenfei Yin and Zaibin Zhang and Zelin Tan and Heng Zhou and Zhong-Zhi Li and Xiangyuan Xue and Yijiang Li and Yifan Zhou and Yang Chen and Chen Zhang and Yutao Fan and Zihu Wang and Songtao Huang and Francisco Piedrahita Velez and Yue Liao and Hongru WANG and Mengyue Yang and Heng Ji and Jun Wang and Shuicheng YAN and Philip Torr and LEI BAI},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=RY19y2RI1O},
note={Survey Certification}
}
```
## Sec2.7 Agentic RL: Algorithms
Clip corresponds to preventing the policy ratio from moving too far from 1 for ensuring stable updates.
KL penalty corresponds to penalizing the KL divergence between the learned policy and the reference policy for ensuring alignment.
| Method | Year | Objective Type | Clip | KL Penalty | Key Mechanism | Signal | Link | Resource |
|--------|------|----------------|------|-------------|---------------|--------|------|----------|
| **_PPO family_** |||||||||
| PPO | 2017 | Policy gradient | Yes | No | Policy ratio clipping | Reward | [Paper](https://arxiv.org/abs/1707.06347) | - |
| VAPO | 2025 | Policy gradient | Yes | Adaptive | Adaptive KL penalty + variance control | Reward + variance signal | [Paper](https://arxiv.org/abs/2504.05118) | - |
| PF-PPO | 2024 | Policy gradient | Yes | Yes | Policy filtration | Noisy reward | [Paper](https://arxiv.org/abs/2409.06957) | [Code](https://github.com/DtYXs/verl/tree/pf-ppo) |
| VinePPO | 2024 | Policy gradient | Yes | Yes | Unbiased value estimates | Reward | [Paper](https://arxiv.org/abs/2410.01679) | [Code](https://github.com/McGill-NLP/VinePPO) |
| PSGPO | 2024 | Policy gradient | Yes | Yes | Process supervision | Process Reward | [Paper](https://openreview.net/forum?id=Cn5Z0MUPZT) | - |
| **_DPO family_** |||||||||
| DPO | 2024 | Preference optimization | No | Yes | Implicit reward related to the policy | Human preference | [Paper](https://proceedings.neurips.cc/paper_files/paper/2023/file/a85b405ed65c6477a4fe8302b5e06ce7-Paper-Conference.pdf) | - |
| β-DPO | 2024 | Preference optimization | No | Adaptive | Dynamic KL coefficient | Human preference | [Paper](https://openreview.net/forum?id=ZfBuhzE556) | [Code](https://github.com/junkangwu/beta-DPO) |
| SimPO | 2024 | Preference optimization | No | Scaled | Use avg log-prob of a sequence as implicit reward | Human preference | [Paper](https://openreview.net/forum?id=3Tzcot1LKb) | [Code](https://github.com/princeton-nlp/SimPO) |
| IPO | 2024 | Implicit preference | No | No | LLMs as preference classifiers | Preference rank | [Paper](https://proceedings.mlr.press/v238/gheshlaghi-azar24a.html) | - |
| KTO | 2024 | Knowledge transfer optimization | No | Yes | Teacher stabilization | Teacher-student logit | [Paper](https://openreview.net/forum?id=iUwHnoENnl) | [Code](https://github.com/ContextualAI/HALOs) [Model](https://huggingface.co/collections/ContextualAI/archangel-65bd45029fa020161b052430) |
| ORPO | 2024 | Online regularized preference optimization | No | Yes | Online stabilization | Online feedback reward | [Paper](https://arxiv.org/abs/2403.07691) | [Code](https://github.com/xfactlab/orpo) [Model](https://huggingface.co/kaist-ai/mistral-orpo-alpha) |
| Step-DPO | 2024 | Preference optimization | No | Yes | Step-wise supervision | Step-wise preference | [Paper](https://arxiv.org/abs/2406.18629) | [Code](htExcerpt of 39,297 characters
Read on GitHub
25
4
3
Aashish Anand
3
1
ZhangShaolei
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:254d56ad854b69bf, llm:Repository name: 'Awesome-AgenticLLM-RL-Papers' — suggests an 'Awesome' curated list of papers on agentic LLMs and reinforcement learning. No README provided but name implies curated literature on agentic LLMs + RL.
matched fp:254d56ad854b69bf, llm:Repository name: 'Awesome-AgenticLLM-RL-Papers' — suggests an 'Awesome' curated list of papers on agentic LLMs and reinforcement learning. No README provided but name implies curated literature on agentic LLMs + RL.
matched fp:254d56ad854b69bf, llm:Repository name: 'Awesome-AgenticLLM-RL-Papers' — suggests an 'Awesome' curated list of papers on agentic LLMs and reinforcement learning. No README provided but name implies curated literature on agentic LLMs + RL.