Vivian Chen

CS PhD Student • UCSD

Profile Photo

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

Amazon Applied Science Intern · Fraud Prevention Jun 2026 – Present · San Diego, CA

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

2025
Jacobs School of Engineering Fellowship, UCSD
2025
Merrill Presidential Scholar, Cornell
2025
Summa Cum Laude Computer Science, Cornell
2025
Phi Beta Kappa Scholarship, Cornell
2023-24
Bowers Undergraduate Research Experience (BURE) Grant
2024
CS Course Staff Exceptional Service Award

Services

Teaching Assistant
  • 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
Volunteer
  • 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.