Instructions to use wangzc9865/SeeNav-Agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wangzc9865/SeeNav-Agent with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="wangzc9865/SeeNav-Agent")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("wangzc9865/SeeNav-Agent")
model = AutoModelForImageTextToText.from_pretrained("wangzc9865/SeeNav-Agent")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use wangzc9865/SeeNav-Agent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wangzc9865/SeeNav-Agent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wangzc9865/SeeNav-Agent",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/wangzc9865/SeeNav-Agent

SGLang

How to use wangzc9865/SeeNav-Agent with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "wangzc9865/SeeNav-Agent" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wangzc9865/SeeNav-Agent",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "wangzc9865/SeeNav-Agent" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wangzc9865/SeeNav-Agent",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use wangzc9865/SeeNav-Agent with Docker Model Runner:
```
docker model run hf.co/wangzc9865/SeeNav-Agent
```

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.

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

🎨 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

🖌️ Training Curves for RFT

🖍️ Testing Curves for OOD-Scenes

📦 Checkpoint

base model	env	🤗 link
Qwen2.5-VL-3B-Instruct-SRGPO	EmbodiedBench-Nav	Qwen2.5-VL-3B-Instruct-SRGPO

🛠️ Usage

Setup

Setup a seperate environment for evaluation according to: EmbodiedBench-Nav and Qwen3-VL to support Qwen2.5-VL-3B-Instruct.
Setup a seperate training environment according to: verl-agent and Qwen3-VL to support Qwen2.5-VL-3B-Instruct.

Evaluation

Use the following command to evaluate the model on EmbodiedBench:

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

Training

verl-agent/examples/srgpo_trainer contains example scripts for SRGPO-based training on EmbodiedBench-Navigation.

Modify run_ebnav.sh according to your setup.
Run the following command:

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:

@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}
}

Downloads last month: 6

Safetensors

Model size

4B params

Tensor type

F32

Model tree for wangzc9865/SeeNav-Agent

Base model

Qwen/Qwen2.5-VL-3B-Instruct

Finetuned

(772)

this model

Paper for wangzc9865/SeeNav-Agent

SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization

Paper • 2512.02631 • Published Dec 2, 2025 • 9