jiafr1802/SpotAgent-rl

🌍 Model Card: SpotAgent

SpotAgent: Grounding Visual Geo-localization in Large Vision-Language Models through Agentic Reasoning

[Project Page]

📝 Citation

If you find SpotAgent useful for your research, please cite our work:

@article{jia2026spotagent,
  title={SpotAgent: Grounding Visual Geo-localization in Large Vision-Language Models through Agentic Reasoning},
  author={Jia, Furong and Dai, L. and Deng, W. and Zhang, F. and Hu, C. and Jiang, D. and Liu, Y.},
  journal={arXiv preprint arXiv:2602.09463},
  year={2026}
}

---

For more details, visit the official project page:
👉 https://jiafr1802.github.io/SpotAgent-Paper/