Improve model card: Add metadata, update paper link and add project page link

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +35 -4
README.md CHANGED
@@ -1,8 +1,35 @@
1
- <div align="center">
 
 
 
 
 
 
 
 
 
 
 
2
 
3
- <h1>Demystifying Reinforcement Learning in Agentic Reasoning<h1>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
 
5
- <p align="center"> <a href="https://arxiv.org/abs/2510.11701"> <img src="https://img.shields.io/badge/Paper-Arxiv-red?logo=arxiv&logoColor=red" alt="Paper on arXiv"/> </a> <a href="https://github.com/Gen-Verse/Open-AgentRL"> <img src="https://img.shields.io/badge/Open--AgentRL-GitHub-black?logo=github&logoColor=white" alt="Open-AgentRL on GitHub"/> </a> <a href="https://huggingface.co/datasets/Gen-Verse/Open-AgentRL-30K"> <img src="https://img.shields.io/badge/30K_RL_Dataset-Hugging%20Face-orange?logo=huggingface&logoColor=yellow" alt="30K RL Dataset"/> </a> <a href="https://huggingface.co/Gen-Verse/DemyAgent-4B"> <img src="https://img.shields.io/badge/DemyAgent--4B-Hugging%20Face-FFCC00?logo=huggingface&logoColor=yellow" alt="DemyAgent-4B Model"/> </a> </p> </div>
 
6
 
7
  ## 🎯 About This Repository
8
  This repository contains the **DemyAgent-4B** model weights, a 4B-sized agentic reasoning model that achieves **state-of-the-art performance** on challenging benchmarks including AIME2024/2025, GPQA-Diamond, and LiveCodeBench-v6.
@@ -60,4 +87,8 @@ We evaluate our models on challenging benchmarks spanning mathematics, science,
60
  journal={arXiv preprint arXiv:2510.11701},
61
  year={2025}
62
  }
63
- ```
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: text-generation
3
+ library_name: transformers
4
+ license: cc-by-nc-4.0
5
+ tags:
6
+ - agentic-reasoning
7
+ - tool-use
8
+ - LLM
9
+ - Qwen
10
+ ---
11
+
12
+ # Demystifying Reinforcement Learning in Agentic Reasoning
13
 
14
+ <div align="center">
15
+ <p align="center">
16
+ <a href="https://huggingface.co/papers/2510.11701">
17
+ <img src="https://img.shields.io/badge/Paper-HuggingFace-red?logo=arxiv&logoColor=red" alt="Paper on Hugging Face"/>
18
+ </a>
19
+ <a href="https://github.com/Gen-Verse/Open-AgentRL">
20
+ <img src="https://img.shields.io/badge/Open--AgentRL-GitHub-black?logo=github&logoColor=white" alt="Open-AgentRL on GitHub"/>
21
+ </a>
22
+ <a href="https://huggingface.co/datasets/Gen-Verse/Open-AgentRL-30K">
23
+ <img src="https://img.shields.io/badge/30K_RL_Dataset-Hugging%20Face-orange?logo=huggingface&logoColor=yellow" alt="30K RL Dataset"/>
24
+ </a>
25
+ <a href="https://huggingface.co/Gen-Verse/DemyAgent-4B">
26
+ <img src="https://img.shields.io/badge/DemyAgent--4B-Hugging%20Face-FFCC00?logo=huggingface&logoColor=yellow" alt="DemyAgent-4B Model"/>
27
+ </a>
28
+ </p>
29
+ </div>
30
 
31
+ **Paper**: [Demystifying Reinforcement Learning in Agentic Reasoning](https://huggingface.co/papers/2510.11701)
32
+ **Project Page**: [Open-AgentRL Collection](https://huggingface.co/collections/Gen-Verse/open-agentrl-68eda4c05755ca5a8c663656)
33
 
34
  ## 🎯 About This Repository
35
  This repository contains the **DemyAgent-4B** model weights, a 4B-sized agentic reasoning model that achieves **state-of-the-art performance** on challenging benchmarks including AIME2024/2025, GPQA-Diamond, and LiveCodeBench-v6.
 
87
  journal={arXiv preprint arXiv:2510.11701},
88
  year={2025}
89
  }
90
+ ```
91
+
92
+ ## 🙏 Acknowledgements
93
+
94
+ This work aims to explore more efficient paradigms for Agentic RL. Our implementation builds upon the excellent codebases of [VeRL](https://github.com/volcengine/verl) and [ReTool](https://github.com/ReTool-RL/ReTool). We sincerely thank these projects for their valuable insights and high-quality implementations, which have greatly facilitated our research.