Instructions to use redai-infra/hybrid-routing-context-rl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use redai-infra/hybrid-routing-context-rl with Transformers:

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

pipe = pipeline("image-text-to-text", model="redai-infra/hybrid-routing-context-rl")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("redai-infra/hybrid-routing-context-rl")
model = AutoModelForMultimodalLM.from_pretrained("redai-infra/hybrid-routing-context-rl", device_map="auto")
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 Settings

vLLM

How to use redai-infra/hybrid-routing-context-rl with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "redai-infra/hybrid-routing-context-rl"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redai-infra/hybrid-routing-context-rl",
		"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/redai-infra/hybrid-routing-context-rl

SGLang

How to use redai-infra/hybrid-routing-context-rl 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 "redai-infra/hybrid-routing-context-rl" \
    --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": "redai-infra/hybrid-routing-context-rl",
		"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 "redai-infra/hybrid-routing-context-rl" \
        --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": "redai-infra/hybrid-routing-context-rl",
		"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 redai-infra/hybrid-routing-context-rl with Docker Model Runner:
```
docker model run hf.co/redai-infra/hybrid-routing-context-rl
```

hybrid-routing-context-rl

The context-compression RL checkpoint (step 40) from the paper Screenshots or Tools? Eliciting Tool Us Context in Hybrid GUI–MCP Computer-UseAgents (arXiv:2608.03327).

A Qwen3-VL-8B-Thinking policy trained with multi-turn GRPO on OSWorld under a train/inference-consistent compressed observation rule: 2-image slip_success` (the screenshot after asuccessful MCP tool call is replaced by a text placeholder). Training and evaluation share the exact same observation policy — that matching is the

Results (OSWorld-MCP `test_all_no_internet`, 309 tasks, greedy ×3)

	accuracy	input cost	peak context (p95)
Base operating point (img4, uncompressed)	33.0%	100%	11.5K tok
This checkpoint (img2 + skip, compressed)	37.8%	53%	−37%

Usage

This is a complete, directly-loadable Qwen3-VL-8B model directory. Deploy it with the compressed observation rule it was trained under — evaluating with the default rich observation underestimates it:

huggingface-cli download redai-infra/hybrid-routing-context-rl --local-dir ckpts/context_rl
MODEL=ckpts/context_rl CONTEXT_POLICY=skip_on_mcp_success MAX_IMAGE_HISTORY_LENGTH=2 \
  bash scripts/run_mcp_eval.sh

Code, configs, and full provenance: https://github.com/redai-infra/hybrid-routing-agent — see results/context_rl/PROVENANCE.md for how every number above is derived, and configs/experiments/context_rl.yaml for the exact training recipe.

Citation

@article{fan2026screenshots,
  title   = {Screenshots or Tools? Eliciting Tool Use and Managing Multimodal
             Context in Hybrid GUI-MCP Computer-Use Agents},
  author  = {Fan, Siqi and Li, Minghao and Ma, Xiaoqian and Tan, Wenhui and
             Huang, Xiusheng and Wu, Juntong and Zhang, Liujie and Shang, Shuo
             and Chen, Weihang},
  journal = {arXiv preprint arXiv:2608.03327},
  year    = {2026},
  url     = {https://arxiv.org/abs/2608.03327}
}

Downloads last month: 36

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for redai-infra/hybrid-routing-context-rl

Base model

Qwen/Qwen3-VL-8B-Thinking

Finetuned

(74)

this model

Dataset used to train redai-infra/hybrid-routing-context-rl

Space using redai-infra/hybrid-routing-context-rl 1

Paper for redai-infra/hybrid-routing-context-rl

Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents

Paper • 2608.03327 • Published 27 days ago • 3