Instructions to use xxwu/Agent-STAR-RL-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xxwu/Agent-STAR-RL-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="xxwu/Agent-STAR-RL-1.5B")
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-1.5B")
model = AutoModelForCausalLM.from_pretrained("xxwu/Agent-STAR-RL-1.5B")
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 xxwu/Agent-STAR-RL-1.5B 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-1.5B"
# 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-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xxwu/Agent-STAR-RL-1.5B

SGLang

How to use xxwu/Agent-STAR-RL-1.5B 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-1.5B" \
    --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-1.5B",
		"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-1.5B" \
        --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-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xxwu/Agent-STAR-RL-1.5B with Docker Model Runner:
```
docker model run hf.co/xxwu/Agent-STAR-RL-1.5B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Agent-STAR-RL-1.5B

This repository contains the Agent-STAR-RL-1.5B model, which is part of the research presented in the paper "Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe".

Agent-STAR is a systematic study of the reinforcement learning (RL) design space for long-horizon tool-using agents using the TravelPlanner testbed. The model is trained using the STAR pipeline: Data Synthesis → SFT → RL.

Model Details

Backbone: Qwen2.5-1.5B-Instruct
Training Stage: Reinforcement Learning (RL)
Primary Task: Long-horizon tool orchestration and planning.
Paper: Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
Repository: GitHub - Agent-STAR
Dataset: Agent-STAR-TravelDataset

According to the paper's findings, smaller models like this 1.5B variant benefit from scale-aware recipes including staged (curriculum-style) rewards and enhanced exploration to handle the complex constraints of multi-turn environments.

Usage

To run ReAct inference using the official implementation, you can use the following command structure:

cd Inference
python3 -u main.py \
  --model xxwu/Agent-STAR-RL-1.5B \
  --save_suffix your_suffix \
  --max_workers 20 \
  --split validation \
  --max_context 32768 \
  --max_turns 60

Note: You will need to prepare the travel database as described in the GitHub repository.

Citation

If you find Agent-STAR helpful to your work, please cite the following:

@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}, 
}