alphaXiv

Explore

State of the Art

Sign In

Labs

Feedback

Browser Extension

We're hiring
PaperBlogResources

SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models

BibTex
Copy
@misc{feiWed Nov 19 2025 16:52:23 GMT+0000 (Coordinated Universal Time)srposelfreferentialpolicy,
      title={SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models},
      author={Senyu Fei and Siyin Wang and Li Ji and Ao Li and Shiduo Zhang and Liming Liu and Jinlong Hou and Jingjing Gong and Xianzhong Zhao and Xipeng Qiu},
      year={Wed Nov 19 2025 16:52:23 GMT+0000 (Coordinated Universal Time)},
      eprint={2511.15605},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2511.15605},
}
GitHub
siiRL
226
HTTPS
https://github.com/sii-research/siiRL
SSH
git@github.com:sii-research/siiRL.git
CLI
gh repo clone sii-research/siiRL
Transform this paper into an audio lecture
Get an engaging lecture and Q&A format to quickly understand the paper in minutes, perfect for learning on the go.
Audio lecture
Q&A format