Update README.md

README.md

@@ -22,8 +22,8 @@ This repository provides trained checkpoints for reward modeling and user-level
 
 ## Links
 
-- 📄 **arXiv Paper**: https://arxiv.org/abs/XXXX.XXXXX  
-- 🤗 **Hugging Face Paper**: https://huggingface.co/papers/XXXX.XXXXX  
+- 📄 **arXiv Paper**: https://arxiv.org/abs/2601.18731  
+- 🤗 **Hugging Face Paper**: https://huggingface.co/papers/2601.18731  
 - 💻 **GitHub Code**: https://github.com/ModalityDance/MRM  
 - 📦 **Hugging Face Collection**: https://huggingface.co/collections/ModalityDance/mrm
 
@@ -155,11 +155,14 @@ print("reward(rejected)=", s_rj.tolist())
 If you use this model or code in your research, please cite:
 
 ```bibtex
-@article{mrm2025,
-  title   = {Meta Reward Modeling for Personalized Alignment},
-  author  = {Author Names},
-  journal = {arXiv preprint arXiv:XXXX.XXXXX},
-  year    = {2025}
+@misc{cai2026adaptsanymetareward,
+      title={One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment}, 
+      author={Hongru Cai and Yongqi Li and Tiezheng Yu and Fengbin Zhu and Wenjie Wang and Fuli Feng and Wenjie Li},
+      year={2026},
+      eprint={2601.18731},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2601.18731}, 
 }
 ```