Yunan (Lucy) Lu

Ph.D. Student, Computer Science · Columbia University

I'm a 2nd-year Ph.D. student in Computer Science at Columbia University advised by Zhou Yu. My research focuses on the evaluation of application-centric LLM-based agent systems, particularly through simulation-driven methods for assessing agent behavior, modeling realistic user interactions, and improving system performance via continuous learning.

I'm happy to chat about research or collaborations — reach me at yl4021@columbia.edu.

Publications

* denotes equal contribution

Under Review

VISTA: A Versatile Interactive User Simulation Toolkit for Agent Evaluation

Yunan Lu*, Ryan Shea*, Yusen Zhang, Zhou Yu

Under review.

Under Review

PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures

Yunan Lu*, Luigi Liu*, Omar Yahia*, Arpit Sharma, Zhou Yu

Under review.

ABS PDF

ICLR 2026

Speculative Actions: A Lossless Framework for Faster Agentic Systems

Naimeng Ye*, Arnav Ahuja*, Georgios Liargkovas*, Yunan Lu*, Kostis Kaffes, Tianyi Peng

In International Conference on Learning Representations (ICLR 2026). (Oral).

ABS PDF Code

EACL 2026

SAGE: A Top-Down Bottom-Up Knowledge-Grounded User Simulator for Multi-turn AGent Evaluation

Ryan Shea*, Yunan Lu*, Liang Qiu, Zhou Yu

In Proceedings of the 21st Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026).

ABS PDF Code

ACL 2024

LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems

Xiao Yu*, Yunan Lu*, Zhou Yu

In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), System Demonstrations.

ABS PDF Code

EMNLP 2023

Mixture of Soft Prompts for Controllable Data Generation

Derek Chen, Celine Lee, Yunan Lu, Domenic Rosati, Zhou Yu

In Findings of the Association for Computational Linguistics: EMNLP 2023.

ABS PDF Code