Wenya Xie
Ph.D. student @ UMN CSE · LLM reasoning, agent memory, personalization
I’m Wenya Xie, a first-year Ph.D. student in Computer Science at the University of Minnesota (UMN), advised by Prof. Zirui Liu. Previously, I worked as a research assistant at CUHK (Shenzhen) with Prof. Benyou Wang and Feng Jiang. I received my bachelor’s degree from Wuhan University.
My research centers on large language models, with a particular focus on agent memory, long-horizon interaction, and personalization.
Currently, I’m exploring:
• Long-horizon state management for LLM agents, including what to store, update, and retrieve across extended interactions.
• Learning from imperfect user feedback to adapt to personalized preferences across turns.
I’m always excited to connect. Questions, ideas, and early-stage thoughts are all welcome. If you have anything you’d like to discuss, feel free to reach out!
news
| Apr 07, 2026 | Two papers accepted to ACL 2026: Memory management for LLM agents and Proactive reasoning in large language models |
|---|---|
| Sep 18, 2025 | One paper accepted to NeurIPS 2025 as an Oral Presentation: reproducible reasoning in FP32. |
| Aug 20, 2025 | One paper accepted to EMNLP 2025 as an Oral Presentation: WordSaladChopper. |