Liyi Chen
Algorithm Engineer, Xiaohongshu Inc. Ph.D., University of Science and Technology of China
Beijing, China
Email: liyichencly@gmail.com, chenliyi@xiaohongshu.com, liyichen@mail.ustc.edu.cn
Google Scholar | DBLP | GitHub

Brief
I am currently an Algorithm Engineer at Xiaohongshu Inc. in Beijing, where I work on LLM post-training for user agent and AI search scenarios. My research and engineering interests lie in large language models, post-training, intelligent agents, and AI search. I received my Ph.D. degree in Computer Science and Technology from University of Science and Technology of China (USTC) in 2025, as a member of the State Key Laboratory of Cognitive Intelligence, under the supervision of Prof. Hui Xiong (ACM Fellow, AAAI Fellow, AAAS Fellow, IEEE Fellow, CAAI Fellow, ACM Distinguished Scientist). Before that, I received my B.Eng. degree from Nanjing University of Aeronautics and Astronautics (NUAA) in 2020 and was recommended to USTC for postgraduate study with the first place in my major. Throughout my undergraduate and graduate studies, I received three National Scholarships, eight First-Class Academic Scholarships, the President's Scholarship of Chinese Academy of Sciences, and Outstanding Graduate honors at both the provincial and university levels. I have published over 10 papers in top-tier international conferences and journals, including NeurIPS, ACL, KDD, SIGIR, WWW, and AAAI.
Highlights
Recruiting
Our team at Xiaohongshu is working on Community Agent and AI Search AskNow (问一问) scenarios. Our team has won Xiaohongshu's Business Breakthrough Award for two consecutive years in 2024 and 2025, the company's highest internal technology award, with million-yuan project funding each year. We are hiring full-time employees, campus hires, and research interns who are interested in LLM post-training, agent systems, and AI search. Please feel free to contact me at chenliyi@xiaohongshu.com if you are interested.

AI Search AskNow

AskNow (问一问) is Xiaohongshu's AI search experience. It synthesizes real user notes and community experiences into structured, actionable answers, such as travel itineraries, must-visit places, food recommendations, and practical tips, while supporting follow-up questions in conversational search.

Education

Professional Experience

Internships

Publications

Preprints

  1. Wei Wu, Peilun Zhou, Liyi Chen*, Qimeng Wang, Chengqiang Lu, Yan Gao, Yi Wu, Yao Hu, Hui Xiong*. Aligning Large Language Models with Searcher Preferences. arXiv preprint arXiv:2603.10473, 2026. [arXiv]
  2. Qianyu Meng, Yanan Wang, Liyi Chen*, Yihang Li, Wei Wu, Wenyuan Jiang, Qimeng Wang, Chengqiang Lu, Yan Gao, Yi Wu, Yao Hu. Agent Harness for Large Language Model Agents: A Survey. Preprints.org 202604.0428.v3, 2026. [Link][GitHub]

Published Papers

  1. Liyi Chen, Panrong Tong, Zhongming Jin, Ying Sun, Jieping Ye*, Hui Xiong*. Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs. In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS'2024), Vancouver, Canada, 2024, 37665-37691.[Link][Code][MIT Technology Review]
  2. Liyi Chen, Ying Sun, Shengzhe Zhang, Yuyang Ye, Wei Wu, Hui Xiong*. Tackling Uncertain Correspondences for Multi-Modal Entity Alignment. In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS'2024), Vancouver, Canada, 2024, 119386-119410. [Link][Code]
  3. Liyi Chen, Chuan Qin*, Ying Sun, Xin Song, Tong Xu, Hengshu Zhu, Hui Xiong*. Collaboration-Aware Hybrid Learning for Knowledge Development Prediction. In Proceedings of the ACM Web Conference 2024 (WWW'2024), Singapore, 2024, 3976-3985. [Link][Code]
  4. Liyi Chen, Zhi Li, Weidong He, Gong Cheng, Tong Xu*, Nicholas Jing Yuan, Enhong Chen. Entity Summarization via Exploiting Description Complementarity and Salience. In IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), Volume: 34, Issue: 11, 2023, 8297-8309. [Link]
  5. Liyi Chen, Zhi Li, Tong Xu*, Han Wu, Zhefeng Wang, Nicholas Jing Yuan, Enhong Chen. Multi-modal Siamese Network for Entity Alignment. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'2022), Washington DC, USA, 2022, 118-126. [Link][Code]
  6. Liyi Chen, Zhi Li, Yijun Wang, Tong Xu*, Zhefeng Wang, Enhong Chen. MMEA: Entity Alignment for Multi-modal Knowledge Graphs. In Proceedings of the 13th International Conference on Knowledge Science, Engineering and Management (KSEM'2020), Hangzhou, China, 2020, 134-147. [Link][Code] (Best Paper Award)
  7. Wei Wu, Liyi Chen*, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu, Yan Gao, Yi Wu, Yao Hu, Hui Xiong*. Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL'2026), San Diego, USA, 2026, Accepted. [arXiv]
  8. Shengzhe Zhang, Liyi Chen, Dazhong Shen, Chao Wang*, Hui Xiong*. Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential Recommendation. In Proceedings of the ACM Web Conference 2025 (WWW'2025), Sydney, Australia, 2025, 3672-3682. [Link]
  9. Wei Wu, Zhuoshi Pan, Kun Fu, Chao Wang, Liyi Chen, Yunchu Bai, Tianfu Wang, Zheng Wang, Hui Xiong. TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP'2025), Suzhou, China, 2025, 21264-21281. [Link][arXiv]
  10. Wei Wu, Chao Wang, Liyi Chen, Mingze Yin, Yiheng Zhu, Kun Fu, Jieping Ye, Hui Xiong, Zheng Wang. Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'2025), Toronto, Canada, 2025, 3216-3227. [Link][arXiv]
  11. Shengzhe Zhang, Liyi Chen, Chao Wang, Shuangli Li, Hui Xiong*. Temporal Graph Contrastive Learning for Sequential Recommendation. In Proceedings of the 38th Annual AAAI Conference on Artificial Intelligence (AAAI'2024), Vancouver, Canada, 2024, 38 (8), 9359-9367. [Link]
  12. Wei Wu, Chao Wang*, Dazhong Shen, Chuan Qin, Liyi Chen, Hui Xiong*. AFDGCF: Adaptive Feature De-correlation Graph Collaborative Filtering for Recommendations. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'2024), Washington D.C., USA, 2024, 1242-1252. [Link]
  13. Lili Zhao, Qi Liu*, Linan Yue, Wei Chen, Liyi Chen, Ruijun Sun, Chao Song. COMI: COrrect and MItigate Shortcut Learning Behavior in Deep Neural Networks. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'2024), Washington D.C., USA, 2024, 218-228. [Link]
  14. Guanqi Zhu, Hanqing Tao, Han Wu, Liyi Chen, Ye Liu, Qi Liu, Enhong Chen*. Text Classification via Learning Semantic Dependency and Association. In Proceedings of the 2022 International Joint Conference on Neural Networks (IJCNN'2022), Padova, Italy, 2022. [Link]
  15. Fake Lin, Weican Cao, Wen Zhang, Liyi Chen, Yuan Hong, Tong Xu, Chang Tan. Knowledge-Enhanced Retrieval: A Scheme for Question Answering. In Proceedings of the 6th China Conference on Knowledge Graph and Semantic Computing (CCKS'2021), Guangzhou, China, 2021, 102-113. [Link]
  16. Shiwei Wu, Joya Chen, Tong Xu*, Liyi Chen, Lingfei Wu, Yao Hu, Enhong Chen. Linking the Characters: Video-oriented Social Graph Generation via Hierarchical-cumulative GCN. In Proceedings of the 29th ACM International Conference on Multimedia (ACM MM'2021), Chengdu, China, 2021, 4716-4724. [Link]

Awards

Services