How to use from
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?"
			}
		]
	}'
Quick Links

Agent-Reflex-8B

Paper HF Paper GitHub Collection SFT Data RL Data

Paper: arXiv:2610.17953 · Hugging Face Papers

Agent-Reflex-8B is Qwen3-8B trained with Agent-Reflex, a framework that elicits proactive reflection in tool-using agents: noticing noisy tool feedback and user corrections, and recovering from them.

Training: Qwen3-8B → ReSFT (54,663 reflective trajectories, 5,127 steps) → ORPO (noisy agentic RL with skill-guided on-policy distillation). Skills are used only during training; the model runs skill-free.

Results

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 82.5 58.6 29.1

Each benchmark is scored with its official metric. Overall is the unweighted mean of the five long-horizon tool-use benchmarks (Table 1 of the paper); AgentNoiseBench is the mean over its τ²-Bench and VitaBench noise settings (Table 2).

Usage

Serve with vLLM (native function calling, thinking on), as in our evaluation:

vllm serve dongguanting/Agent-Reflex-8B --served-model-name Qwen/Qwen3-8B \
  --tensor-parallel-size 8 --max-model-len 40960 \
  --enable-auto-tool-choice --tool-call-parser hermes --reasoning-parser deepseek_r1

The full evaluation suite (τ²-Bench, BFCL V4, ACEBench, VitaBench, AgentNoiseBench, ToolSandbox) is in the GitHub repo.

Citation

@misc{dong2026agentreflex,
  title={Agent-Reflex: Teaching Language Agents to Act Reflectively},
  author={Guanting Dong and Xinyu Yang and Jiajie Jin and Yuyang Hu and Xiaoshuai Song and Yifei Chen and Xiaoxi Li and Jiejun Tan and Yutao Zhu and Tat-Seng Chua and Ji-Rong Wen and Zhicheng Dou},
  year={2026},
  eprint={2610.17953},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2610.17953},
}
Downloads last month
575
Safetensors
Model size
8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for dongguanting/Agent-Reflex-8B

Finetuned
Qwen/Qwen3-8B
Finetuned
(2,367)
this model
Quantizations
2 models

Datasets used to train dongguanting/Agent-Reflex-8B

Collection including dongguanting/Agent-Reflex-8B

Paper for dongguanting/Agent-Reflex-8B