Yibo Peng彭艺博

Péng Yìbó (pronounced "penɡ EE-bor")

Carnegie Mellon University

Pittsburgh, Pennsylvania
Yibo Peng

About

I am Yibo Peng, a Research Assistant at Carnegie Mellon University. Advised by Prof. Beidi Chen, my research focuses on the security of AI agents. I also collaborate with Prof. Huaxiu Yao on multimodel large language models and with Prof. Graham Neubig on code agents through the OpenHands project.

I recently received my Master's degree in Artificial Intelligence Engineering from Carnegie Mellon University. During my studies, I had the privilege of being advised by Prof. Daniel Fried, with a focus on Code Generation and Retrieval-Augmented Generation (RAG).

My research interests lie in addressing the core challenges for AI agents: enhancing their multimodal reasoning capabilities in complex environments, optimizing the efficiency of multi-agent collaboration, and ensuring the safety of their behavior.

🎓 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 yibopcmu@gmail.com.

Selected Publications

Context-Contrastive Reinforcement Learning for Robust MLLM Reading
Yibo Peng*, Peng Xia*, Ding Zhong*, Kaide Zeng, Siwei Han, Yiyang Zhou, Jiaqi Liu, Ruiyi Zhang, Ruiyi Zhang, Huaxiu Yao
Submitted to CVPR 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
Accepted by ResponsibleFM @ NeurIPS 2025
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
Submitted to ICLR 2026
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