Instructions to use xupy21/ContextRL_Qwen3_8B_Agentic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xupy21/ContextRL_Qwen3_8B_Agentic with Transformers:

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

pipe = pipeline("text-generation", model="xupy21/ContextRL_Qwen3_8B_Agentic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xupy21/ContextRL_Qwen3_8B_Agentic")
model = AutoModelForCausalLM.from_pretrained("xupy21/ContextRL_Qwen3_8B_Agentic")
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 Settings

vLLM

How to use xupy21/ContextRL_Qwen3_8B_Agentic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xupy21/ContextRL_Qwen3_8B_Agentic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xupy21/ContextRL_Qwen3_8B_Agentic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xupy21/ContextRL_Qwen3_8B_Agentic

SGLang

How to use xupy21/ContextRL_Qwen3_8B_Agentic 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 "xupy21/ContextRL_Qwen3_8B_Agentic" \
    --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": "xupy21/ContextRL_Qwen3_8B_Agentic",
		"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 "xupy21/ContextRL_Qwen3_8B_Agentic" \
        --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": "xupy21/ContextRL_Qwen3_8B_Agentic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xupy21/ContextRL_Qwen3_8B_Agentic with Docker Model Runner:
```
docker model run hf.co/xupy21/ContextRL_Qwen3_8B_Agentic
```

ContextRL-Qwen3-8B-Agentic

This is the agentic (long-horizon) model released with the paper Context-Aware RL for Agentic and Multimodal LLMs. It is fine-tuned from Qwen3-8B, a general-purpose model, using ContextRL, a context-aware reinforcement learning method that augments standard GRPO with an auxiliary context-selection objective to improve fine-grained context grounding in long-horizon agent trajectories.

Results

Across 5 long-horizon benchmarks (2 in-distribution agentic coding, 3 out-of-distribution), ContextRL improves over the standard GRPO baseline by +1.5 points on average, while improving every individual benchmark.

Benchmark	Base	RL (GRPO)	ContextRL (Ours)
SWE-Bench Verified	5.00	6.20	7.00
SWE-Bench Lite	2.70	2.70	4.00
LiveCodeBench v6	44.6	46.3	47.4
LongBench v2 (Overall)	31.6	31.8	33.2
LongBench v2 (Long)	27.8	26.9	29.6
NIAH	98.8	98.5	99.0

Metrics: SWE-Bench Verified/Lite resolve rate (%), LiveCodeBench v6 solve rate (%), LongBench v2 accuracy (%), NIAH mean recall (%). On the long-context tasks (LongBench v2, NIAH) where standard outcome-based GRPO struggles or regresses, ContextRL surpasses both the base model and the RL baseline, demonstrating strong out-of-distribution generalization.

Usage

This model follows the same interface as Qwen3-8B and can be loaded with transformers. Training and evaluation code, data construction pipelines, and detailed configurations are available in the repository: 👉 https://github.com/xupy2003/ContextAwareRL Please refer to the repo's README for environment setup, inference scripts, and reproduction instructions.