Improve model card: Add metadata, paper/code links, and comprehensive details

This PR significantly enhances the model card for `SeeNav-Agent` by:

- Adding `library_name: transformers` metadata, which enables the "How to use" widget on the model page, given the model's compatibility with the Transformers library.
- Adding `pipeline_tag: image-text-to-text` metadata, improving the model's discoverability for relevant tasks on the Hugging Face Hub.
- Updating the paper link to the official Hugging Face paper page: [SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization](https://huggingface.co/papers/2512.02631).
- Including a direct link to the official [GitHub repository](https://github.com/WzcTHU/SeeNav-Agent).
- Providing a comprehensive content section with an overview, highlights, detailed summary, results, checkpoint information, and usage instructions (evaluation and training scripts) directly from the GitHub README.
- Ensuring proper citation information is included.

These changes make the model card more informative and user-friendly for the community.

README.md

@@ -1,5 +1,102 @@
 ---
 base_model:
 - Qwen/Qwen2.5-VL-3B-Instruct
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
-arxiv.org/abs/2512.02631
+
+# SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization
+
+This repository contains the official implementation for the paper [SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization](https://huggingface.co/papers/2512.02631).
+
+<div align="center">
+    <a href="https://github.com/WzcTHU/SeeNav-Agent"><img src="https://img.shields.io/badge/GitHub-Code-blue.svg?logo=github&" alt="GitHub Code"></a>
+    <a href="https://huggingface.co/wangzc9865/SeeNav-Agent"><img src="https://img.shields.io/badge/🤗&nbsp;-HuggingFace-blue" alt="Hugging Face Model"></a>
+</div>
+
+## Overview
+We propose **SeeNav-Agent**, a novel LVLM-based embodied navigation framework that includes a zero-shot dual-view visual prompt technique for the input side and an efficient RFT algorithm named SRGPO for post-training. Existing Vision-Language Navigation (VLN) agents often suffer from perception, reasoning, and planning errors, which SeeNav-Agent aims to mitigate through its proposed techniques.
+
+## 🚀 Highlights
+
+*   🚫 **Zero-Shot Visual Prompt:** No extra training for performance improvement with visual prompt.
+*   🗲 **Efficient Step-Level Advantage Calculation:** Step-Level groups are randomly sampled from the entire batch.
+*   📈 **Significant Gains:** +20.0pp (GPT4.1+VP) and +5.6pp (Qwen2.5-VL-3B+VP+SRGPO) improvements on EmbodiedBench-Navigation.
+
+## 📖 Summary
+<div style="text-align: center;">
+  <img src="https://github.com/WzcTHU/SeeNav-Agent/raw/main/SeeNav/figs/framework.png" width="100%">
+</div>
+
+*   🎨 **Dual-View Visual Prompt:** We apply visual prompt techniques directly on the input dual-view image to reduce the visual hallucination.
+*   🔁 **Step Reward Group Policy Optimization (SRGPO):** By defining a state-independent verifiable process reward function, we achieve efficient step-level random grouping and advantage estimation.
+
+## 📋 Results on EmbodiedBench-Navigation
+
+### 📝 Main Results
+<div align="center">
+    <img src="https://github.com/WzcTHU/SeeNav-Agent/raw/main/SeeNav/figs/results.png" width="50%"/>
+</div>
+
+### 🖌️ Training Curves for RFT
+<div align="center">
+    <img src="https://github.com/WzcTHU/SeeNav-Agent/raw/main/SeeNav/figs/training_curves.png" width="50%"/>
+</div>
+
+### 🖍️ Testing Curves for OOD-Scenes
+<div align="center">
+    <img src="https://github.com/WzcTHU/SeeNav-Agent/raw/main/SeeNav/figs/ood_val.png" width="50%"/>
+</div>
+
+### 📦 Checkpoint
+
+| base model | env | 🤗 link |
+| :--: | :--: | :--: |
+| Qwen2.5-VL-3B-Instruct-SRGPO| EmbodiedBench-Nav | [Qwen2.5-VL-3B-Instruct-SRGPO](https://huggingface.co/wangzc9865/SeeNav-Agent) |
+
+## 🛠️ Usage
+
+### Setup
+
+1.  Setup a seperate environment for evaluation according to: [EmbodiedBench-Nav](https://github.com/EmbodiedBench/EmbodiedBench) and [Qwen3-VL](https://github.com/QwenLM/Qwen3-VL) to support Qwen2.5-VL-3B-Instruct.
+
+2.  Setup a seperate training environment according to: [verl-agent](https://github.com/langfengQ/verl-agent) and [Qwen3-VL](https://github.com/QwenLM/Qwen3-VL) to support Qwen2.5-VL-3B-Instruct.
+
+### Evaluation
+
+Use the following command to evaluate the model on EmbodiedBench:
+
+```bash
+conda activate <your_env_for_eval>
+cd SeeNav
+python testEBNav.py
+```
+
+Hint: you need to first set your endpoint, API-key and api_version in [`SeeNav/planner/models/remote_model.py`](https://github.com/WzcTHU/SeeNav-Agent/blob/main/SeeNav/planner/models/remote_model.py)
+
+### Training
+
+[`verl-agent/examples/srgpo_trainer`](https://github.com/WzcTHU/SeeNav-Agent/blob/main/verl-agent/examples/srgpo_trainer) contains example scripts for SRGPO-based training on EmbodiedBench-Navigation.
+
+1.  Modify [`run_ebnav.sh`](https://github.com/WzcTHU/SeeNav-Agent/blob/main/verl-agent/examples/srgpo_trainer/run_ebnav.sh) according to your setup.
+
+2.  Run the following command:
+
+```bash
+conda activate <your_env_for_train>
+cd verl-agent
+bash examples/srgpo_trainer/run_ebnav.sh
+```
+
+## 📚 Citation
+
+If you find this work helpful in your research, please consider citing:
+
+```bibtex
+@article{wang2025seenav,
+  title={SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization},
+  author={Zhengcheng Wang and Zichuan Lin and Yijun Yang and Haobo Fu and Deheng Ye},
+  journal={arXiv preprint arXiv:2512.02631},
+  year={2025}
+}
+```