Naicheng Yu

I am a master's student in Computer Science and Engineering at UC San Diego. Before UCSD, I received my B.E. in Software Engineering from Zhejiang University.

My research focuses on LLM agents and benchmarking and evaluation.

I am applying to PhD programs for Fall 2027 and am always happy to discuss research ideas or potential collaborations.

Portrait of Naicheng Yu

Research Interests

Benchmarking and Evaluation

Understanding what benchmarks actually measure, and designing evaluations whose results are reliable and interpretable.

Self-Evolving Agents

Building agents that accumulate knowledge from their past attempts and use it to keep improving, rather than starting from scratch on every task.

Chain-of-Thought Monitoring

Studying whether a model's reasoning faithfully reflects its behavior, and how reasoning traces can help oversee increasingly capable models.

Agent Memory Systems

Designing how agents store, organize, and share memory over long horizons and across multiple agents.

Publications

Your Benchmark Is an Empirical Measure Over Difficulty

Yifan Sun*, Naicheng Yu*, Jiawen Gong*, Jingyan Shen, Huan Zhang

NeurIPS 2026 Evaluations & Datasets Track · [Paper] [Code] [Project] [Data]

Meta-Delta: Evolving Knowledge through Global Review for LLM-Driven Optimization

Naicheng Yu*, Yiming Huang*, Junxia Cui, Lingjun Mao, Xinkai Zou, Ziche Liu, Letian Peng, Jingbo Shang

NeurIPS 2026 Workshop on Meta-Agents

How do Visual Attributes Influence Web Agents? A Comprehensive Evaluation of User Interface Design Factors

Kuai Yu*, Naicheng Yu*, Han Wang, Rui Yang, Huan Zhang

ACL 2026 Findings · [Paper] [Code] [Project]

Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead

Zhongming Yu, Naicheng Yu, Hejia Zhang, Wentao Ni, Mingrui Yin, Jiaying Yang, Yujie Zhao, Jishen Zhao

Architecture 2.0 Workshop, ASPLOS 2026 · [Paper]

MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models

Han Wang*, Yifan Sun*, Brian Ko*, Mann Talati, Jiawen Gong, Zimeng Li, Naicheng Yu, Xucheng Yu, Wei Shen, Vedant Jolly, Huan Zhang

COLM 2026 · [Paper] [Code]

Can LLMs Discover Scientific Laws in Real and Parallel Worlds?

Yiming Huang*, Ziche Liu*, Zhuohang Wu, Yiqian Wang, Junxia Cui, Xinkai Zou, Lingjun Mao, Nan Huang, Naicheng Yu, Kaijie Zhu, Yue Ma, Kun Zhou, Letian Peng, Jingbo Shang

Under review · [Paper] [Code] [Project] [Data]

* Equal contribution.

Education

University of California, San Diego

Master of Science in Computer Science and Engineering

Sep 2025 – Present

University of California, Berkeley

Visiting Student

Jan 2024 – May 2024

Zhejiang University

Bachelor of Engineering in Software Engineering

Sep 2021 – Jul 2025

Teaching Experience

Principles in Computer Architecture (CSE 240A)

Teaching Assistant · UC San Diego

Fall 2026

Fundamentals of Software Engineering

Teaching Assistant · Zhejiang University

Fall 2023

Academic Service