Instructions to use dongguanting/Agent-Reflex-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dongguanting/Agent-Reflex-8B with Transformers:

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

pipe = pipeline("text-generation", model="dongguanting/Agent-Reflex-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dongguanting/Agent-Reflex-8B")
model = AutoModelForCausalLM.from_pretrained("dongguanting/Agent-Reflex-8B", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dongguanting/Agent-Reflex-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dongguanting/Agent-Reflex-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dongguanting/Agent-Reflex-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dongguanting/Agent-Reflex-8B

SGLang

How to use dongguanting/Agent-Reflex-8B 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 "dongguanting/Agent-Reflex-8B" \
    --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": "dongguanting/Agent-Reflex-8B",
		"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 "dongguanting/Agent-Reflex-8B" \
        --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": "dongguanting/Agent-Reflex-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dongguanting/Agent-Reflex-8B with Docker Model Runner:
```
docker model run hf.co/dongguanting/Agent-Reflex-8B
```

dongguanting commited on 19 days ago

Commit

e563d1d

verified ·

1 Parent(s): f16c7a3

Update results and citation

Browse files

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -30,8 +30,9 @@ Training: Qwen3-8B → **ReSFT** (54,663 reflective trajectories, 5,127 steps)
 | Model | VitaBench | τ²-Bench | BFCL V4 | ACEBench | ToolSandbox | **Overall** | AgentNoiseBench |
 | --- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
 | Qwen3-8B | 11.4 | 26.2 | 40.4 | 54.0 | 69.1 | 40.2 | 12.3 |
-| EnvScaler-8B | 15.8 | 37.9 | 47.6 | 60.0 | 80.5 | 48.4 | 17.6 |
-| **Agent-Reflex-8B** | **17.5** | **54.9** | **48.9** | **76.0** | **81.8** | **55.8** | **21.4** |
 ## Usage
@@ -48,9 +49,10 @@ The full evaluation suite (τ²-Bench, BFCL V4, ACEBench, VitaBench, AgentNoiseB
 ## Citation
 ```bibtex
-@article{agentreflex2026,
   title  = {Agent-Reflex: Teaching Language Agents to Act Reflectively},
-  author = {Anonymous},
   year   = {2026}
 }
 ```

 | Model | VitaBench | τ²-Bench | BFCL V4 | ACEBench | ToolSandbox | **Overall** | AgentNoiseBench |
 | --- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
 | Qwen3-8B | 11.4 | 26.2 | 40.4 | 54.0 | 69.1 | 40.2 | 12.3 |
+| EnvScaler-8B | 15.8 | 37.9 | 47.6 | 72.5 | 80.5 | 50.9 | 18.2 |
+| Agent-World-8B | 14.5 | 54.6 | 51.4 | 72.0 | 75.6 | 53.6 | – |
+| **Agent-Reflex-8B** | **17.5** | **62.1** | **52.9** | **78.0** | **81.8** | **58.5** | **29.1** |
 ## Usage
 ## Citation
 ```bibtex
+@article{dong2026agentreflex,
   title  = {Agent-Reflex: Teaching Language Agents to Act Reflectively},
+  author = {Dong, Guanting and Yang, Xinyu and Jin, Jiajie and Hu, Yuyang and Song, Xiaoshuai and Chen, Yifei and Li, Xiaoxi and Tan, Jiejun and Zhu, Yutao and Chua, Tat-Seng and Wen, Ji-Rong and Dou, Zhicheng},
+  journal = {arXiv preprint},
   year   = {2026}
 }
 ```