Instructions to use teng-pan/Agent-R2-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use teng-pan/Agent-R2-4B with Transformers:

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

pipe = pipeline("text-generation", model="teng-pan/Agent-R2-4B")
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("teng-pan/Agent-R2-4B")
model = AutoModelForCausalLM.from_pretrained("teng-pan/Agent-R2-4B", 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 teng-pan/Agent-R2-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "teng-pan/Agent-R2-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teng-pan/Agent-R2-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/teng-pan/Agent-R2-4B

SGLang

How to use teng-pan/Agent-R2-4B 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 "teng-pan/Agent-R2-4B" \
    --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": "teng-pan/Agent-R2-4B",
		"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 "teng-pan/Agent-R2-4B" \
        --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": "teng-pan/Agent-R2-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use teng-pan/Agent-R2-4B with Docker Model Runner:
```
docker model run hf.co/teng-pan/Agent-R2-4B
```

teng-pan commited on 5 days ago

Commit

558cc78

verified ·

1 Parent(s): 25c632d

Add base model results; drop Evaluation, Training Data, Limitations, Citation

Browse files

Files changed (1) hide show

README.md +5 -34

README.md CHANGED Viewed

@@ -21,20 +21,18 @@ It is the model introduced in *Agent-R²: Scaling Agents for Realistic Productiv
 ## Results
-| Benchmark | Agent-R²-4B | Qwen3-235B-A22B-Thinking-2507 |
-|---|---|---|
-| GDPval  | **51.0** | 48.0 |
-| OfficeQA | **14.8** | 13.8 |
-Scores are as reported in the paper. Both benchmarks evaluate end-to-end task completion on realistic occupational tasks.
 ## Model Details
 - **Base model:** Qwen3-4B-Thinking-2507
 - **Parameters:** 4B
 - **Training stages:** SFT → rubric-based RL
-- **Training data:** 4k real-source task instances; real occupational seeds, corpus-derived workflow evidence, and authentic web-sourced files
-- **Context / turns:** multi-turn agentic rollouts with file-manipulation tools provided by the harness
 ## Intended Use
@@ -73,33 +71,6 @@ print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_token
 For best results, expose the file tools used during training and give the model an explicit, verifiable deliverable specification. The model benefits from being told what the final artifact must contain and how it will be checked.
-## Training Data
-Task instances were synthesized by a real-source pipeline: occupational seeds and workflow evidence were drawn from a web corpus, candidate tasks were filtered from 10k down to 4k, and each retained task was paired with real web-sourced attachments and a deliverable-level rubric. Because the attachments are authentic web documents, they may contain personal names, contact details, or other information present in the original public sources.
-## Evaluation
-Evaluated on GDPval (51.0) and OfficeQA (14.8) using the protocol described in the paper. See the paper for full setup, rubric definitions, and per-task breakdowns.
-## Limitations
-- Trained and evaluated on English-language professional tasks; performance on other languages and domains is not established.
-- Deliverable quality is judged by rubrics; a high rubric score does not guarantee factual correctness on every claim.
-- The model can still hallucinate file contents or fabricate numbers when the grounding evidence is ambiguous — always review generated artifacts before use.
-- Long rollouts on large file collections are compute-intensive.
-- Web-sourced training attachments may carry imperfect OCR, stale data, or copyrighted content.
-## Citation
-```bibtex
-@article{pan2026agentr2,
-  title   = {Agent-R$^2$: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis},
-  author  = {Pan, Teng and Wang, Zixuan and Yan, Yuchen and Wu, Qifei and Chen, Yao and Qu, Yingqi and Zhang, Ruiqing and Shen, Yongliang},
-  journal = {arXiv preprint},
-  year    = {2026}
-}
-```
 ## Links
 - Code: https://github.com/ZJU-REAL/Agent-R2

 ## Results
+| Benchmark | Qwen3-4B-Thinking-2507 (base) | Agent-R²-4B | Qwen3-235B-A22B-Thinking-2507 |
+|---|---|---|---|
+| GDPval  | 32.4 | **51.0** | 48.0 |
+| OfficeQA | 2.2 | **14.8** | 13.8 |
+Scores are as reported in the paper. All benchmarks evaluate end-to-end task completion on realistic occupational tasks.
 ## Model Details
 - **Base model:** Qwen3-4B-Thinking-2507
 - **Parameters:** 4B
 - **Training stages:** SFT → rubric-based RL
 ## Intended Use
 For best results, expose the file tools used during training and give the model an explicit, verifiable deliverable specification. The model benefits from being told what the final artifact must contain and how it will be checked.
 ## Links
 - Code: https://github.com/ZJU-REAL/Agent-R2