Snowflake/Arctic-AWM-14B

<h1 align="center">Arctic-AWM-14B</h1>

<h3 align="center">Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning</h3>

<p align="center"> <a href="https://github.com/Raibows">Zhaoyang Wang¹</a>, <a href="https://www.canwenxu.net/">Canwen Xu²</a>, <a href="https://www.snowflake.com/en/blog/authors/boyi-liu/">Boyi Liu²</a>, <a href="https://yitewang.github.io/">Yite Wang²</a>, <a href="https://lillianwei-h.github.io/">Siwei Han¹</a>,<br/> <a href="https://yaozhewei.github.io/">Zhewei Yao²</a>, <a href="https://www.huaxiuyao.io/">Huaxiu Yao¹</a>, <a href="https://www.snowflake.com/en/blog/authors/yuxiong-he/">Yuxiong He²</a> </p> <p align="center"> ¹UNC-Chapel Hill &nbsp; ²Snowflake AI Research &nbsp; </p>

Overview

Arctic-AWM-14B is a multi-turn tool-use agent model trained with agentic reinforcement learning on Qwen3-14B, using the fully synthetic environments from AgentWorldModel-1K.

The model is trained to interact with tool-use environments exposed via a unified MCP (Model Context Protocol) interface, enabling strong multi-turn agentic capabilities.

For detailed usage of the model, please visit https://github.com/Snowflake-Labs/agent-world-model.

Resources

Related resources are also available, please check:

Citation

If you find this resource useful, please kindly cite:

@article{wang2026agentworldmodelinfinity,
      title={Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning}, 
      author={Zhaoyang Wang and Canwen Xu and Boyi Liu and Yite Wang and Siwei Han and Zhewei Yao and Huaxiu Yao and Yuxiong He},
      year={2026},
      eprint={2602.10090},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2602.10090}, 
}