RynnUnify-Agentic-Reasoner

RynnUnify-Agentic-Reasoner is the reasoning model from the RynnUnify family after reinforcement learning (RL) post-training, exported as a standalone Qwen3-VL model.

• Architecture: Qwen3VLForConditionalGeneration (Qwen3-VL-8B-Instruct based)
• Precision: bfloat16, 4 safetensors shards (~17.5 GB)

Usage

from transformers import AutoModelForCausalLM, AutoProcessor

model = AutoModelForCausalLM.from_pretrained(
    "Alibaba-DAMO-Academy/RynnUnify-Agentic-Reasoner",
    torch_dtype="bfloat16",
    device_map="auto",
)
processor = AutoProcessor.from_pretrained("Alibaba-DAMO-Academy/RynnUnify-Agentic-Reasoner")

Part of the RynnUnify collection: RynnUnify-Base | RynnUnify-Agentic-Reasoner | RynnUnify-WAM-RoboCasa

Citation

@misc{rynnunify2026,
  title={RynnUnify: Towards Unified Embodied Brain},
  author={Minghao Zhu and Bohan Hou and Kun Xiang and Zixuan Wang and Yinzhou Tang and Yifei Yang and Zhikai Wang and Tianyi Zhang and Kehan Li and Haoyu Zhao and Siteng Huang and Leigang Qu and Sicong Leng and Dongchi Huang and Mingxiu Chen and Shijian Lu and Yue Wang and Xiaodan Liang and Zhenyu Zeng and Deli Zhao and Chengju Liu and Jianfei Yang and Xin Li},
  year={2026},
}