Instructions to use xxwu/Agent-STAR-RL-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xxwu/Agent-STAR-RL-7B with Transformers:

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

pipe = pipeline("text-generation", model="xxwu/Agent-STAR-RL-7B")
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-7B")
model = AutoModelForCausalLM.from_pretrained("xxwu/Agent-STAR-RL-7B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use xxwu/Agent-STAR-RL-7B 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-7B"
# 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-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xxwu/Agent-STAR-RL-7B

SGLang

How to use xxwu/Agent-STAR-RL-7B 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-7B" \
    --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-7B",
		"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-7B" \
        --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-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xxwu/Agent-STAR-RL-7B with Docker Model Runner:
```
docker model run hf.co/xxwu/Agent-STAR-RL-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Agent-STAR-RL-7B

Agent-STAR-RL-7B is a 7B parameter model based on Qwen2.5-7B-Instruct, fine-tuned using Reinforcement Learning (RL) for long-horizon tool-use tasks.

This model is a key artifact of the paper Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe.

Model Description

The model was developed using the STAR [Data Synthesis → SFT → RL] pipeline, a unified post-training recipe for scaling RL in complex, multi-turn environments. It is specifically optimized for TravelPlanner, a challenging testbed requiring tool orchestration to satisfy multifaceted commonsense and hard constraints.

As per the systematic study in the paper, the 7B variant leverages GRPO (Group Relative Policy Optimization) with a dense SUM reward for optimized performance and faster convergence.

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

Training Pipeline

Data Synthesis: Generation of synthetic queries and successful trajectories.
SFT: Fine-tuning from the backbone using ~1K successful trajectories.
RL: Scale-aware reinforcement learning tuning.

Usage

This model is designed to be used within a ReAct-style agentic framework. For reproducing the results on TravelPlanner, it is recommended to use the inference code provided in the official repository.

Inference Example

From the Agent-STAR repository root:

cd Inference
python3 -u main.py \
  --model xxwu/Agent-STAR-RL-7B \
  --save_suffix test_run \
  --max_workers 20 \
  --split validation \
  --max_context 32768 \
  --max_turns 60

Citation

@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}, 
}