Instructions to use PolarSeeker/LongSeeker-30B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PolarSeeker/LongSeeker-30B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="PolarSeeker/LongSeeker-30B-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PolarSeeker/LongSeeker-30B-SFT")
model = AutoModelForCausalLM.from_pretrained("PolarSeeker/LongSeeker-30B-SFT")
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 PolarSeeker/LongSeeker-30B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PolarSeeker/LongSeeker-30B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PolarSeeker/LongSeeker-30B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PolarSeeker/LongSeeker-30B-SFT

SGLang

How to use PolarSeeker/LongSeeker-30B-SFT 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 "PolarSeeker/LongSeeker-30B-SFT" \
    --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": "PolarSeeker/LongSeeker-30B-SFT",
		"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 "PolarSeeker/LongSeeker-30B-SFT" \
        --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": "PolarSeeker/LongSeeker-30B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PolarSeeker/LongSeeker-30B-SFT with Docker Model Runner:
```
docker model run hf.co/PolarSeeker/LongSeeker-30B-SFT
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents

Update — May 27: The model has been updated. Please use the latest version for evaluation and deployment.

LongSeeker is a long-horizon search agent that introduces Context-ReAct, a novel paradigm for elastic context orchestration. Unlike standard ReAct agents that passively accumulate observations, LongSeeker dynamically reshapes its working context using five atomic meta-operations: Skip, Compress, Rollback, Snippet, and Delete. This allows the agent to preserve critical evidence, summarize resolved information, discard unhelpful branches, and control context size—achieving reliable and efficient long-horizon reasoning.

Highlights

Strong long-horizon search performance: LongSeeker achieves 61.5 on BrowseComp, 62.5 on BrowseComp-ZH, 78.0 on xbench-2505, and 77.7 on GAIA-text, demonstrating competitive capability across both web search and general agent benchmarks.
Elastic context orchestration for search agents: We introduce Context-ReAct, a new agentic paradigm that jointly generates reasoning, context meta-operations, and tool calls, enabling agents to dynamically decide when, where, and how to reshape their working context during long-horizon search.
Comprehensive and fine-grained context control: Context-ReAct defines five atomic operations—Skip, Compress, Rollback, Snippet, and Delete—forming an expressively complete yet efficient operation set for multi-resolution context management.
Efficient context management at extended horizons: LongSeeker maintains a stable working context of around 15k tokens even across long trajectories, using only a small fraction of its 256k context window while avoiding the rapid context growth of standard ReAct agents.