Instructions to use intuit/agent-tool-optimizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use intuit/agent-tool-optimizer with Transformers:

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

pipe = pipeline("text-generation", model="intuit/agent-tool-optimizer")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("intuit/agent-tool-optimizer")
model = AutoModelForCausalLM.from_pretrained("intuit/agent-tool-optimizer")
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 intuit/agent-tool-optimizer with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/intuit/agent-tool-optimizer

SGLang

How to use intuit/agent-tool-optimizer 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 "intuit/agent-tool-optimizer" \
    --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": "intuit/agent-tool-optimizer",
		"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 "intuit/agent-tool-optimizer" \
        --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": "intuit/agent-tool-optimizer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use intuit/agent-tool-optimizer with Docker Model Runner:
```
docker model run hf.co/intuit/agent-tool-optimizer
```

kevindong-intuit commited on Feb 26

Commit

c986295

1 Parent(s): a7aef48

add arxiv

Browse files

Files changed (1) hide show

README.md +24 -0

README.md CHANGED Viewed

@@ -38,6 +38,30 @@ We study tool interface improvement as a scalable complement to agent fine-tunin
 ---
 ## Recommended prompt (trace-free)
 This is the **canonical inference prompt** used for trace-free tool description generation (also available as `tool_prompt.txt` in the `tool-optimizer` repo).

 ---
+## Paper (arXiv)
+This model is released alongside the preprint:
+- **Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use**
+  Ruocheng Guo, Kaiwen Dong, Xiang Gao, Kamalika Das
+  arXiv:2602.20426 (2026) — [paper](https://arxiv.org/abs/2602.20426)
+### Citation
+```bibtex
+@misc{guo2026learningrewritetooldescriptions,
+      title={Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use},
+      author={Ruocheng Guo and Kaiwen Dong and Xiang Gao and Kamalika Das},
+      year={2026},
+      eprint={2602.20426},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI},
+      url={https://arxiv.org/abs/2602.20426},
+}
+```
+---
 ## Recommended prompt (trace-free)
 This is the **canonical inference prompt** used for trace-free tool description generation (also available as `tool_prompt.txt` in the `tool-optimizer` repo).