Add metadata and improve model card for RLAnything

Hi! I'm Niels from the Hugging Face community science team.

I've opened this PR to improve the discoverability and usability of this model:
- Added `pipeline_tag: image-text-to-text` to reflect its multimodal capabilities (Qwen3-VL based).
- Added `library_name: transformers` as the repository contains the standard configuration files for the library.
- Updated the model card title to match the framework name "RLAnything" and added links to the paper and code.

Let me know if you have any questions!

README.md

@@ -1,24 +1,34 @@
 ---
 license: mit
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags:
+- reinforcement-learning
+- agent
+- gui-agent
+- vl-model
+---
 ---
 
-
-# Introduction to TraDo
+# RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
 
 [Paper](https://arxiv.org/abs/2602.02488) | [Code](https://github.com/Gen-Verse/Open-AgentRL) | [Blog](https://yinjjiew.github.io/projects/rlanything/)
 
-We introduce **RLAnything**, a reinforcement learning framework forges environment, policy and reward model in a completely dynamic system to enhance the training signals and improve the whole system.
-
-* **Integrated Feedback for Policy:** The policy is trained with integrated outcome and step-wise signals from reward model.
-* **Consistency Feedback for Reward Model:** The Reward model is jointly optimized by consistency feedback, further improves policy training.
-* **Critic Feedback for Environment:** Our theory-motivated automatic environment adaptation improves training for both the reward and policy models by leveraging critic feedback from each.
+**RLAnything** is a reinforcement learning framework that dynamically forges environment, policy, and reward models through closed-loop optimization, amplifying learning signals and strengthening the overall RL system for any LLM or agentic scenarios.
 
+### Highlights
 
+*   **Integrated Feedback for Policy:** The policy is trained with integrated outcome and step-wise signals from the reward model, outperforming traditional outcome-only signals.
+*   **Consistency Feedback for Reward Model:** The reward model is jointly optimized via consistency feedback, which in turn further improves policy training.
+*   **Critic Feedback for Environment:** Theory-motivated automatic environment adaptation improves training for both the reward and policy models by leveraging critic feedback from each, enabling learning from experience.
 
 <p align="center">
   <img src="https://github.com/yinjjiew/Data/raw/main/rlanything/rlanythingoverview.png" width="100%"/>
 </p>
 
+### Performance
+
+RLAnything yields substantial gains across various representative LLM and agentic tasks, boosting Qwen3-VL-8B-Thinking by 9.1% on OSWorld and Qwen2.5-7B-Instruct by 18.7% and 11.9% on AlfWorld and LiveBench, respectively.
 
 <p align="center">
   <img src="https://github.com/yinjjiew/Data/raw/main/rlanything/rlanythingscaleosworld.png" width="70%"/>
@@ -30,15 +40,13 @@ We introduce **RLAnything**, a reinforcement learning framework forges environme
 </p>
 
 
-# Citation
+## Citation
 
-```
+```bibtex
 @article{wang2026rlanything,
   title={RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System},
   author={Wang, Yinjie and Xie, Tianbao and Shen, Ke and Wang, Mengdi and Yang, Ling},
   journal={arXiv preprint arXiv:2602.02488},
   year={2026}
 }
-```
-
-
+```