Instructions to use lixiaoxi45/DeepAgent-QwQ-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lixiaoxi45/DeepAgent-QwQ-32B with Transformers:

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

pipe = pipeline("text-generation", model="lixiaoxi45/DeepAgent-QwQ-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lixiaoxi45/DeepAgent-QwQ-32B")
model = AutoModelForCausalLM.from_pretrained("lixiaoxi45/DeepAgent-QwQ-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lixiaoxi45/DeepAgent-QwQ-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lixiaoxi45/DeepAgent-QwQ-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lixiaoxi45/DeepAgent-QwQ-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lixiaoxi45/DeepAgent-QwQ-32B

SGLang

How to use lixiaoxi45/DeepAgent-QwQ-32B 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 "lixiaoxi45/DeepAgent-QwQ-32B" \
    --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": "lixiaoxi45/DeepAgent-QwQ-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "lixiaoxi45/DeepAgent-QwQ-32B" \
        --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": "lixiaoxi45/DeepAgent-QwQ-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lixiaoxi45/DeepAgent-QwQ-32B with Docker Model Runner:
```
docker model run hf.co/lixiaoxi45/DeepAgent-QwQ-32B
```

DeepAgent: A General Reasoning Agent with Scalable Toolsets

DeepAgent is an end-to-end deep reasoning agent that performs autonomous thinking, tool discovery, and action execution within a single, coherent reasoning process. It is designed to overcome the limitations of traditional, predefined workflows by maintaining a global perspective on tasks and dynamically discovering tools.

Paper: DeepAgent: A General Reasoning Agent with Scalable Toolsets
Repository: GitHub - RUC-NLPIR/DeepAgent

Key Features

Unified Agentic Reasoning: DeepAgent operates in a single stream of thought, autonomously reasoning about the task and discoverying necessary tools.
Autonomous Memory Folding: To handle long-horizon interactions, DeepAgent introduces a mechanism that compresses past interactions into structured episodic, working, and tool memories, reducing context explosion while preserving critical information.
ToolPO Strategy: An end-to-end reinforcement learning strategy tailored for general tool use, utilizing LLM-simulated APIs and fine-grained credit assignment for tool invocation.

Performance

Extensive experiments on eight benchmarks, including general tool-use tasks (ToolBench, API-Bank, TMDB, Spotify, ToolHop) and downstream applications (ALFWorld, WebShop, GAIA, HLE), demonstrate that DeepAgent consistently outperforms baselines across both labeled-tool and open-set tool retrieval scenarios.

Citation

If you find this work helpful, please cite the paper:

@misc{deepagent,
      title={DeepAgent: A General Reasoning Agent with Scalable Toolsets}, 
      author={Xiaoxi Li and Wenxiang Jiao and Jiarui Jin and Guanting Dong and Jiajie Jin and Yinuo Wang and Hao Wang and Yutao Zhu and Ji-Rong Wen and Yuan Lu and Zhicheng Dou},
      year={2025},
      eprint={2510.21618},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2510.21618}, 
}

Downloads last month: 13

Safetensors

Model size

1.12M params

Tensor type

BF16

Paper for lixiaoxi45/DeepAgent-QwQ-32B

DeepAgent: A General Reasoning Agent with Scalable Toolsets

Paper • 2510.21618 • Published Oct 24, 2025 • 103