Instructions to use xxwu/Agent-STAR-RL-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xxwu/Agent-STAR-RL-3B with Transformers:

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

pipe = pipeline("text-generation", model="xxwu/Agent-STAR-RL-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xxwu/Agent-STAR-RL-3B")
model = AutoModelForCausalLM.from_pretrained("xxwu/Agent-STAR-RL-3B")
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 Settings

vLLM

How to use xxwu/Agent-STAR-RL-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xxwu/Agent-STAR-RL-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xxwu/Agent-STAR-RL-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xxwu/Agent-STAR-RL-3B

SGLang

How to use xxwu/Agent-STAR-RL-3B 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 "xxwu/Agent-STAR-RL-3B" \
    --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": "xxwu/Agent-STAR-RL-3B",
		"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 "xxwu/Agent-STAR-RL-3B" \
        --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": "xxwu/Agent-STAR-RL-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xxwu/Agent-STAR-RL-3B with Docker Model Runner:
```
docker model run hf.co/xxwu/Agent-STAR-RL-3B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Agent-STAR-RL-3B

This repository contains the Agent-STAR-RL-3B model, a 3B parameter Large Language Model fine-tuned for long-horizon tool orchestration tasks. It was introduced in the paper Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe.

Model Description

Agent-STAR is a unified post-training pipeline consisting of [Data Synthesis → SFT → RL]. This specific checkpoint is the RL-tuned version based on the Qwen2.5-3B-Instruct backbone, optimized for the TravelPlanner benchmark.

The model was developed to handle complex, multi-turn agentic environments where it must call various tools to satisfy multifaceted constraints. According to the research findings, smaller models like this 3B variant benefit from staged rewards and enhanced exploration during the RL phase to achieve high performance.

Resources

Paper: Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
GitHub Repository: WxxShirley/Agent-STAR
Dataset: Agent-STAR-TravelDataset

Inference

To run inference with this model, please refer to the instructions and ReAct-based inference pipeline provided in the official GitHub repository.

Citation

If you find Agent-STAR helpful to your work, please consider citing:

@misc{wu2026agentstar,
      title={Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe}, 
      author={Xixi Wu and Qianguo Sun and Ruiyang Zhang and Chao Song and Junlong Wu and Yiyan Qi and Hong Cheng},
      year={2026},
      eprint={2603.21972},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2603.21972}, 
}

Acknowledgements

We appreciate the open-sourced rLLM framework and the authors of TravelPlanner for providing the benchmark and resources that supported this research.