UC Berkeley EECS · Fall 2027 PhD Applicant

Building and evaluating agents that can work in the real world.

I work at the intersection of AI agents, robot learning, and embodied intelligence. My research focuses on the data, environments, and evaluation systems needed to make long-horizon agents capable and reliable.

I am an EECS undergraduate at UC Berkeley, where I work with Prof. Dawn Song at Berkeley RDI/BAIR and am a co-first author and core contributor to Agents' Last Exam (ALE). I am also working with Zhuo Xu and Prof. Masayoshi Tomizuka on a large-scale robot-learning data benchmark, and with Prof. Avideh Zakhor on UAV perception.

01

Recent

Building a robot-learning data benchmark using large-scale egocentric manipulation and interaction data.

Agents' Last Exam is available on arXiv with an open evaluation framework for long-horizon, real-world agent tasks.

A robot delivery system integrating VLA and agentic workflows was demonstrated at CES 2026.

02

Research

Robot Learning · DataR02

Robot-Learning Data Benchmark

An ongoing effort with Zhuo Xu and Prof. Masayoshi Tomizuka to build a large-scale benchmark for robot learning. I work on cleaning and curating heterogeneous egocentric manipulation and human-object interaction data, including EgoVerse, EgoDex, and HOI4D.

The goal is to turn diverse human demonstrations into reliable, usable resources for training and evaluating embodied systems.

Computer Vision · UAVV03

UAV-to-UAV Detection & Tracking

Research with Prof. Avideh Zakhor on zero-shot UAV-to-UAV detection and multi-object tracking under high-speed motion and strong ego-motion. I develop PyTorch pipelines that integrate optical-flow-based tracking with detection and tracking baselines.

This work targets reliable perception when objects are small, motion is fast, and background dynamics are substantial.

Embodied Systems · VLAE04

Robot Delivery with VLA

At Starbot, I worked on integrating vision-language-action models and agentic workflows for robot planning and control in a real delivery system. The system was demonstrated at CES 2026.

This experience connected foundation-model reasoning with the constraints of embodied execution and deployment.

03

Selected Publication

2026

Agents' Last Exam

Yiyou Sun*, Xinyang Han*, Weichen Zhang*, Yuanbo Pang*, Tianyu Wang*, et al.

arXiv:2606.05405 · * core/equal contribution

A benchmark for evaluating AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes.

04

Experience

2025 - Present

Berkeley RDI / BAIR

Research Assistant · Prof. Dawn Song · Agent evaluation and RLVR

Current

Robot-Learning Data Benchmark

Robotics Research · Zhuo Xu and Prof. Masayoshi Tomizuka

2026 - Present

UC Berkeley EECS URAP

Research Assistant · Prof. Avideh Zakhor · UAV perception

2026 - Present

Equile

Founding Engineer · Sandboxed agent runtimes and infrastructure

2025 - 2026

Starbot

Robotics AI Engineering Intern · VLA and robot delivery

Get in touch

I am applying for Fall 2027 PhD positions.

I am interested in research on foundation-model agents, robot learning, embodied intelligence, and the data and evaluation systems that connect them.