I am a final-year Ph.D. student in Computer Science at University of Illinois Urbana-Champaign, fortunately advised by Prof. Jiawei Han. Before that, I was an undergraduate student in Electrical Engineering of Tsinghua University, fortunately advised by Prof. Yong Li. During the past, I spent time at Apple AIML, Google Research, Amazon Search, and Microsoft Research (both Redmond and Beijing).

My research is supported by Apple PhD Fellowship and Yunni and Maxine Pao Memorial Fellowship. For further information, please see my CV (last update: 2025.10.02).

Research Interests: My research centers on LLM Post-Training, approached from three key perspectives: augmentation, alignment, and reasoning/agents.

• Augmentation – Enhancing foundation models with external data sources to improve their capabilities (RAG-FT, Graph-CoT).
• Alignment – Developing methods to better align LLMs with human preferences and values (LarPO).
• Reasoning & Agents – Unlocking the reasoning and agentic capabilities of LLMs through reinforcement learning (Search-R1, Search-R1++).

I invent Search-R1, one of the first open-source frameworks to enable LLMs’ reasoning and agentic capability through reinforcement learning (3k+ Github stars).

Previously, I worked on foundation model + graphs / IR / science with awesome github repos on Large Language Models on Graphs and Multimodal Learning on Graphs with a survey paper. Feel free to have a look!

I will be on the job market starting in Fall 2025. If you believe I might be a good fit for your institution or organization, I’d love to connect! — please feel free to reach out at bowenj4[AT]illinois.edu.

Selected Publications [Full List]

• An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents
  Bowen Jin, Jinsung Yoon, Priyanka Kargupta, Sercan O. Arik, Jiawei Han.
  preprint 2025.
  [PDF] [Code] [Resource]

• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
  Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan O. Arik, Dong Wang, Hamed Zamani, Jiawei Han.
  COLM 2025.
  [PDF] [Code] [Resource] [Media] [English Record] [Chinese Record] 3k+ Github stars

• LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
  Bowen Jin, Jinsung Yoon, Zhen Qin, Ziqi Wang, Wei Xiong, Yu Meng, Jiawei Han, Sercan O. Arik.
  ICML 2025.
  [PDF] [Code]

• Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  Bowen Jin, Jinsung Yoon, Jiawei Han, Sercan O. Arik.
  ICLR 2025.
  [PDF] [Resource]

• Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs
  Bowen Jin, Chulin Xie, Jiawei Zhang, Kashob Kumar Roy, Yu Zhang, Suhang Wang, Yu Meng, Jiawei Han.
  ACL 2024 (findings).
  [PDF] [Code] [Data]

• Language Models as Semantic Indexers
  Bowen Jin, Hansi Zeng, Guoyin Wang, Xiusi Chen, Tianxin Wei, Ruirui Li, et al.
  ICML 2024.
  [PDF] [Code]

• Patton: Language Model Pretraining on Text-rich Networks
  Bowen Jin, Wentao Zhang, Yu Zhang, Yu Meng, Xinyang Zhang, Qi Zhu, Jiawei Han.
  ACL 2023 (Oral).
  [PDF] [Code]

• Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks
  Bowen Jin, Yu Zhang, Yu Meng, Jiawei Han.
  ICLR 2023 (Poster).
  [PDF] [Code]

Education

• University of Illinois Urbana-Champaign, Ph.D. in Computer Science (2021 - Present).
• Tsinghua University, B.S. in Electrical Engineering and Statistics (2017 - 2021).

Miscellaneous

I started to play a traditional Chinese instrument, Sheng at the age of eight. Here is a concert record of mine. Hope you enjoy it!:)

I’m a “universal” ball fan ⚽️🏀🎾 and enjoy working out 🏋️. If you cannot find me in office, catch me at the gym. 😃

Contact

Email: bowenj4[AT]illinois.edu