Rong-Xi Tan 谭荣熙

Selected work

1. 

   A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization

   Ming Chen, Rong-Xi Tan, Ke Xue, Yu-Jie Zhou, Taiye Lu, Zhi-Xuan Gao, Peng Xie, Zijun Shen, Chen Lu, Haopu Shang, and Chao Qian.

   arXiv preprint 2610.12183, 2026.

   [paper][code]

   [bib]

   BibTeX Download .bib

   @article{chen2026closer,
     title={A closer look at agentic {BBO}: {B}enchmarking {LLM} agents for black-box optimization},
     author={Ming Chen and Rong-Xi Tan and Ke Xue and Yu-Jie Zhou and Taiye Lu and Zhi-Xuan Gao and Peng Xie and Zijun Shen and Chen Lu and Haopu Shang and Chao Qian},
     journal={arXiv:2610.12183},
     year={2026}
   }

2. 

   Global Patterns and Feasible Improvement Potential of Phosphorus Use Efficiency in Cereal Croplands

   Yishen Sun^*, Han Hu^*, Rong-Xi Tan^*, Julian Helfenstein, Richard W. McDowell, Baojing Gu, Haowei Ni, Weigen Huang, Jixian Ding, Ke Xue, Chao Qian, Jizhong Zhou, Zhi-Hua Zhou, Jiabao Zhang, and Yuting Liang.

   Nature Food, 7(9): 869–877, 2026.

   [paper][code]

   [bib]

   BibTeX Download .bib

   @article{sun2026global,
     title={Global patterns and feasible improvement potential of phosphorus use efficiency in cereal croplands},
     author={Yishen Sun and Han Hu and Rong-Xi Tan and Julian Helfenstein and Richard W. McDowell and Baojing Gu and Haowei Ni and Weigen Huang and Jixian Ding and Ke Xue and Chao Qian and Jizhong Zhou and Zhi-Hua Zhou and Jiabao Zhang and Yuting Liang},
     journal={Nature Food},
     volume={7},
     number={9},
     pages={869--877},
     year={2026}
   }

3. 

   Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning

   Ming Chen^*, Sheng Tang^*, Rong-Xi Tan^*, Ziniu Li, Jiacheng Chen, Ke Xue, and Chao Qian.

   Proceedings of the 43rd International Conference on Machine Learning (ICML), PMLR 306: 16875–16909, 2026.

   [paper][code]

   [bib]

   BibTeX Download .bib

   @inproceedings{chen2026beyond,
     title={Beyond token-level supervision: {U}nlocking the potential of decoding-based regression via reinforcement learning},
     author={Ming Chen and Sheng Tang and Rong-Xi Tan and Ziniu Li and Jiacheng Chen and Ke Xue and Chao Qian},
     booktitle={Proceedings of the 43rd International Conference on Machine Learning (ICML)},
     pages={16875--16909},
     address={Seoul, South Korea},
     year={2026}
   }

4. 

   BBOPlace-Bench: Benchmarking Black-Box Optimization for Chip Placement

   Ke Xue^*, Ruo-Tong Chen^*, Rong-Xi Tan^*, Xi Lin, Yunqi Shi, Siyuan Xu, Mingxuan Yuan, and Chao Qian.

   IEEE Transactions on Evolutionary Computation, 2026, in press.

   [paper][code]

   [bib]

   BibTeX Download .bib

   @article{xue2026bboplace,
     title={{BBOPlace-Bench}: {B}enchmarking black-box optimization for chip placement},
     author={Ke Xue and Ruo-Tong Chen and Rong-Xi Tan and Xi Lin and Yunqi Shi and Siyuan Xu and Mingxuan Yuan and Chao Qian},
     journal={IEEE Transactions on Evolutionary Computation},
     year={2026}
   }

5. 

   Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings

   Rong-Xi Tan^*, Ming Chen^*, Ke Xue, Yao Wang, Yaoyuan Wang, Sheng Fu, and Chao Qian.

   Proceedings of the 42nd International Conference on Machine Learning (ICML), PMLR 267: 58499–58544, 2025.

   [paper][code]

   [bib]

   BibTeX Download .bib

   @inproceedings{tan2025towards,
     title={Towards universal offline black-box optimization via learning language model embeddings},
     author={Rong-Xi Tan and Ming Chen and Ke Xue and Yao Wang and Yaoyuan Wang and Sheng Fu and Chao Qian},
     booktitle={Proceedings of the 42nd International Conference on Machine Learning (ICML)},
     pages={58499--58544},
     address={Vancouver, Canada},
     year={2025}
   }

   Oral presentation, Foundation Models in the Wild Workshop at ICLR 2025.

   Also featured in GECCO 2026 Companion, Hot off the Press, pp. 85–86.

6. 

   Offline Model-Based Optimization by Learning to Rank

   Rong-Xi Tan, Ke Xue, Shen-Huan Lyu, Haopu Shang, Yao Wang, Yaoyuan Wang, Sheng Fu, and Chao Qian.

   Proceedings of the 13th International Conference on Learning Representations (ICLR), 2025.

   [paper][code]

   [bib]

   BibTeX Download .bib

   @inproceedings{tan2025offline,
     title={Offline model-based optimization by learning to rank},
     author={Rong-Xi Tan and Ke Xue and Shen-Huan Lyu and Haopu Shang and Yao Wang and Yaoyuan Wang and Sheng Fu and Chao Qian},
     booktitle={Proceedings of the 13th International Conference on Learning Representations (ICLR)},
     address={Singapore},
     year={2025}
   }

Honors & Awards

• Jun 2025Research results reported by NSFC.
• Dec 2024Nanjing University Top-Grade Scholarship — the university’s highest honor.
• Sep 2024National Science Foundation for Undergraduates (国家自然科学基金本科生项目).
• Apr 2024Merit Student of Jiangsu Province.
• Nov 2023Bailu Scholarship, Nanjing University.
• Jul 2023Pacemaker to Outstanding Students, Nanjing University.
• May 2023One Hundred Outstanding Youths of Qixia District, Communist Youth League of Qixia District.
• Nov 2022Second Prize Nationwide in the National University Mathematical Modeling Competition.

Invited Talks

• Sep 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings.
  LEAD Workshop by SCUT · Virtual.

Beyond Research

My Chinese name is 谭荣熙 (Tan Rongxi), pronounced approximately as /tɑːm wɪŋ ‘heɪ/ in Cantonese.

I enjoy Cantopop and am a fan of Joey Yung—especially 心之科學. I also enjoy going to the gym, jogging, and playing badminton.