Yibo Peng彭艺博

Péng Yìbó (pronounced "penɡ EE-bor")

University of California, Berkeley

Berkeley, California
Yibo Peng

About

I am Yibo Peng, a Research Assistant at UC Berkeley in the Wagner Research Group, advised by Prof. David Wagner and working closely with PhD student Sizhe Chen. My recent research focuses on AI security in real-world applications. I also closely collaborate with Prof. Beidi Chen on Code Agent Security and Prof. Huaxiu Yao on multimodal large language models.

I earned my Master's degree in Artificial Intelligence Engineering from CMU, where I worked with Prof. Daniel Fried and PhD student Zora Zhiruo Wang on code generation, and with Prof. Graham Neubig on code agents.

Broadly, my research aims to address core challenges for AI agents: enhancing multimodal reasoning, optimizing collaboration, and ensuring security and reliability.

🎓 I am actively seeking Ph.D. opportunities for Fall 2026. If you are interested in my work or potential collaborations, please feel free to contact me at yibopengcmu@gmail.com.

News

[Feb 2026] 🔥 I joined UC Berkeley as a Research Assistant in Prof. David Wagner's group, working on AI security.
[Jan 2026] 🔥 One first-author paper was accepted by ICLR 2026.
[Dec 2025] 🔥 I will attend NeurIPS 2025 in San Diego, CA. Excited to catch up with old and new friends!
[Jun 2025] 🔥 I will be joining Prof. Beidi Chen's InfiniAI Lab @ CMU.

Selected Publications

MMedAgent-RL
MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning
Peng Xia*, Yibo Peng*, Jinglu Wang*, Kaide Zeng, Xian Wu, Xiangru Tang, Hongtu Zhu, Yun Li, Yan Lu, Huaxiu Yao
Accepted by International Conference on Learning Representations (ICLR), 2026.
Code Agents Safety
When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?
Yibo Peng*, James Song*, Lei Li*, Xinyu Yang, Mihai Christodorescu, Ravi Mangal, Corina Pasareanu, Haizhong Zheng, Beidi Chen
Submitted to ACL 2026 (ARR Oct, Meta Review: 4)
Accepted by ResponsibleFM @ NeurIPS 2025
Simple OCR
SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read
Yibo Peng*, Peng Xia*, Ding Zhong*, Kaide Zeng, Siwei Han, Yiyang Zhou, Jiaqi Liu, Ruiyi Zhang, Huaxiu Yao
Submitted to ACL 2026 (ARR Jan)
Long-context Code Generation
Can Long-Context Language Models Solve Repository-Level Code Generation?
Yibo Peng, Zora Zhiruo Wang, Daniel Fried
arXiv preprint, 2025

Services

Reviewer: CVPR 2026, NeurIPS 2025 workshop, ICML 2025 workshop