Scholar
Yibo Peng
Google Scholar ID: hyU4axsAAAAJ
Carnegie Mellon University
Citations & Impact
Citations
13
H-index
1
i10-index
1
Publications
2
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- Published several papers, including: 'When 'Correct' Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?', 'MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning', and 'Can Long-Context Language Models Solve Repository-Level Code Generation?'.
Research Experience
- Currently a Research Assistant at Carnegie Mellon University, advised by Prof. Beidi Chen, focusing on the security of AI agents; collaborating with Prof. Huaxiu Yao on multimodal large language models; and working with Prof. Graham Neubig on code agents through the OpenHands project.
Education
- Master's degree in Artificial Intelligence Engineering from Carnegie Mellon University, advised by Prof. Daniel Fried, with a focus on Code Generation and Retrieval-Augmented Generation (RAG).
Background
- Research interests include enhancing the multimodal reasoning capabilities of AI agents in complex environments, optimizing the efficiency of multi-agent collaboration, and ensuring the safety of their behavior. Current research focuses on the security of AI agents, multimodal large language models, and code agents.
Miscellany
- Hobbies include playing the piano, violin, and guqin, Latin dancing, hiking, rock climbing, photography, Chinese calligraphy, and seal carving. Core philosophy is being a dedicated foodie and a champion of the perfect nap.
