Update README.md

README.md

@@ -96,3 +96,17 @@ Physical-AI Coevolution: It drives the "coevolution" of Large Language Models (L
 Knowledge-to-Action Translation: The model leverages its seven AI layers architecture to transform textual knowledge from scientific literature into structured, actionable steps, overcoming the "erudite scholar" limitation where AI possess knowledge but lacks the capacity for physical interaction.
 
 Self-Driving Labs Integration: It serves as the cognitive core for robotic boxes (embodied AI), enabling robots to interpret natural language prompts, reason over mechanistic context, and execute multi-step tasks like material characterization and performance verification.
+
+## 7. Citation
+
+If you use this work, please cite:
+
+```bibtex
+@article{chen2026rlm,
+  title={Agentic Robotic Boxes for Perovskite Solar Cell Fabrication with Recipe Language Model},
+  author={Chen, Zijian and Yu, Wenjin and Wu, Chuang and Chen, Feibei and Wang, Zixuan and Zhou, Chao and You, Yimeng and Li, Shaojie and Zhu, Qiyuan and Ma, Ning and Sun, Yao and Li, Donghui and Fanady, Billy and Jiang, Shengchou and Yan, Zhongliang and Zhou, Shumin and Li, Liang and Hsieh, Chang-Yu and Bai, Yang and Xiao, Lixin and Chung, Chi-yung and Chan, Ching-chuen and Cui, Zhanfeng and Gr{\"a}tzel, Michael and Zhao, Haitao},
+  journal={Engineering},
+  year={2026},
+  doi={10.1016/j.eng.2026.04.002}
+}
+```