Ph.D. StudentUniversity of Washington
I am a Ph.D. student in the Network Security Lab at the University of Washington, advised by Professor Radha Poovendran.
I explore the capabilities and limits of AI agents through synthetic data and evaluation. My recent work spans visual reasoning, automated research, and evaluating AI against human judgment and priorities. Across these settings, I ask: How far can AI agents advance on their own, and how do we know they are truly getting better?
2025 SummerAmazon Web Services — Agent-Driven SQL Generation and Web Visualization.
Introduced an expert-grounded benchmark for visual aesthetics across art, photography, and illustration, revealing a substantial gap between 20 frontier vision-language models and expert judgment.
Studied whether automated research agents can produce convincing but unsound papers that deceive LLM reviewers, and evaluated weaknesses in automated peer review.
Best Paper Award, Agents4Science 2025
Developed a benchmark of 130 agentic tasks across 35 occupations, evaluating workflows that human experts prioritize for delegation and grading outputs with task-specific rubrics.
Adopted by Meta Muse Spark, Kimi K3, and Qwen3.8
Created large-scale synthetic visual logic puzzles using a rule-to-image pipeline. Applied reinforcement learning to improve vision-language models' logical reasoning and transfer across reasoning tasks.
Conference Reviewer: ICML, NeurIPS, ACL
Our paper BadScientist was accepted to ACL 2026.
BadScientist won a Best Paper Award at Agents4Science 2025.
I joined Amazon Web Services in Seattle for a summer internship.