I am a PhD student at the College of Information Science and Technology (IST) at Penn State University since 2022. My advisor is Professor Qingyun Wu. Prior to joining IST, I received my Master’s degree in AI & ML at Imperial College London, and my Bachelor’s degree in Computer Science at the University of California, Davis.

Research Intern 2024 @ Micosoft Research, Redmond.
Research Intern 2025 @ Micosoft Research, Redmond.

My research interests focuses on Large Language Models (LLMs), specifically on Multi-Agent LLM systems and Reinforcement Learning (RL) for LLMs.

I am looking for full-time research scientist industry positions (preferrably in NA) starting June 2026. Feel free to email: ykw5399@psu.edu!

Projects

Open-source LLM agents framework: AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation (45k stars). Project GitHub. (My role: co-creator, maintainer)

Aboslute Zero RLVR training (1.4k stars). Project GitHub. (My role: co-creator, maintainer)

Publications

Absolute zero: Reinforced self-play reasoning with zero data
Andrew Zhao, Yiran Wu, Yang Yue, Tong Wu, Quentin Xu, Matthieu Lin, Shenzhi Wang, Qingyun Wu, Zilong Zheng, Gao Huang
[paper] [github]

StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
Yiran Wu, Tianwei Yue, Shaokun Zhang, Chi Wang, Qingyun Wu. COLM 2024.
[paper] [github]

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
Yifan Zeng*, Yiran Wu*, Xiaoyun Zhang, Huazheng Wang, Qingyun Wu. arxiv preprint arXiv:2403.04783
[paper] [github]

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. COLM 2024.
[paper] [github]

MathChat: Converse to Tackle Challenging Math Problems with LLM Agents Yiran Wu, Feiran Jia, Shaokun Zhang, Hangyu Li, Erkang Zhu, Yue Wang, Yin Tat Lee, Richard Peng, Qingyun Wu, and Chi Wang. ICLR 2024 Workshop on LLMAgents.
[paper] [github]

Unified off-policy learning to rank: a reinforcement learning perspective
Zeyu Zhang, Yi Su, Hui Yuan, Yiran Wu, Rishab Balasubramanian, Qingyun Wu, Huazheng Wang, Mengdi Wang. Advances in Neural Information Processing Systems 36.
[paper] [github]

Automated object detection in experimental data using combination of unsupervised and supervised methods
Yiran Wu, Zhen Wang, Crystal M Ripplinger, Daisuke Sato. Frontiers in Physiology 13, 805161
[paper]