Hi, I’m Vivian (Yiwei) Chen, a first year Ph.D. student in Computer Science at the University of California, San Diego. I am fortunate enough to be jointly advised by Prof. Taylor Berg-Kirkpatrick and Prof. Rose Yu.
Research
My research centers on LLM agents and AI for science. I’m particularly interested in agentic evaluation — understanding how agents acquire evidence, reason causally, and commit to decisions under uncertainty. I’m also interested in reinforcement learning for agents, causal and statistical reasoning, data-efficient modeling, and low-resource NLP.
My current work at UCSD includes ACED-Bench, a benchmark for evaluating whether LLM agents can actively acquire causal evidence and act on it, and Zephyrus, an agentic framework for weather science — both advised by Prof. Taylor Berg-Kirkpatrick and Prof. Rose Yu. Previously, I worked with Prof. Kilian Weinberger on diffusion-guided language modeling (Findings, ACL 2024) and with Prof. Yoav Artzi on retrospective learning from interactions (ACL 2025 Oral).
News
- 06/2026: I joined Amazon as an Applied Science Intern on the Fraud Prevention team in San Diego, working on LLM-based fraud investigation agents.
- 2026: Our paper ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence is under review.
- 12/2025: Our paper Zephyrus: An Agentic Framework for Weather Science was presented at the NeurIPS 2025 Workshop on AI4Science.
- 06/2025: Our paper Retrospective Learning from Interactions has been selected for an oral presentation at ACL 2025.
- 05/2025: I graduated from Cornell with a B.A. in Computer Science, Math, and Linguistics.
Selected Publications
Industry
Building an LLM-based fraud investigation agent that autonomously explores historical transaction data, forms hypotheses about emerging fraud patterns, and generates interpretable rule-based mitigation strategies. Designing RL rewards and training workflows to optimize the agent's investigation policy using a rule-evaluation simulator as the environment.
Awards
Services
- CS 4782: Introduction to Deep Learning
- CS 4780: Machine Learning (twice)
- CS 4740: Natural Language Processing
- CS 2800: Discrete Structures
- CS 2802: Honors Discrete Structures
- Peer Mentor, Women In Computing at Cornell (WICC)
- Girls Who Code Instructor
- Translator, Cornell Translator Interpreter Program
- Staff, INFO 1998: Introduction to Machine Learning (Student-led class)
Miscellaneous
I'm a huge musical theatre fan. I worked for Tony Awards · China as a subtitle translator in 2024.
I like singing, reading, and watching movies. I quite enjoy learning languages, and I'm currently learning Japanese.
For sports, I like skiing and figure skating, and I play table tennis. I will definitely try surfing in San Diego!
I also do a bit of seal cutting in my spare time.