I am a second year PhD student at Software and Societal Systems Department, School of Computer Science, Carnegie Mellon University, co-advised by Christian Kästner and Chris Timperley. I work on safety/security for software with ML/LLM-Agent components, and AI for software safety/security.

Before joining CMU, I received my B.Eng. in Computer Science and B.Ec. in Economics and Finance at Tsinghua University, where I was fortunate to be advised by Prof. Maosong Sun and Prof. Junliang Xing.

I also undertook a summer research internship at CMU’s Software and Societal Systems Department, co-advised by Prof. Christian Kästner and Prof. Sherry Tongshuang Wu.

Publications

Aarya Doshi, Yining Hong, Congying Xu, Eunsuk Kang, Alexandros Kapravelos, Christian Kästner. Towards Verifiably Safe Tool Use for LLM Agents. Accepted at International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER), April 2026.

Yining Hong, Christopher S. Timperley, Christian Kästner. From Hazard Identification to Controller Design: Proactive and LLM-Supported Safety Engineering for ML-Powered Systems. In Proceedings of the International Conference on AI Engineering - Software Engineering for AI (CAIN), April 2025. [.pdf]

Chenyang Yang, Yining Hong, Grace Lewis, Tongshuang Wu, and Christian Kästner. What Is Wrong with My Model? Identifying Systematic Problems with Semantic Data Slicing. In Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering (ASE), Los Alamitos, CA: IEEE Computer Society, November 2024. [.pdf]

Yining Hong, Fanchao Qi, Maosong Sun. Two Heads Are Better Than One: Exploiting Both Sequence and Graph Models in AMR-To-Text Generation. [.pdf]

Teaching Experience

I was a volunteer teaching assistant at the Center for Student Learning and Development at Tsinghua University. I offered drop-in tutoring for computer science and finance courses.