Yixuan (Mark) Xie 「谢沂烜」

Hi, this is Mark!

I am a MSCS student at University of Illinois, Urbana Champaign, advised by Professor Jiawei Han. Before that, I did my undergrad at UIUC (2022–2026), earning a B.S. in Computer Science and Statistics with Highest Honors.

My research interests include:

Memory for LLM agent self-improvement and continual learning
Retrieval-augmented generation (RAG) and search agents

News

Oct 15, 2026	MemComposer submitted to the Oct. 2026 cycle of ACL Rolling Review.
Sep 20, 2026	CaseMem and PyRAG submitted to ICLR 2027.
May 26, 2026	Started as a summer RA on memory for search agents, in collaboration with researchers at Amazon.
May 15, 2026	Graduated from UIUC with a B.S in CS & Stats; continuing my M.S. in CS with Prof. Jiawei Han.

Selected Publications

MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning

Yixuan Xie, Xueqiang Xu , Xinyi Fan , Xinxi Lyu , Tao Feng , Xing Fan , Chenlei Guo , Jie Hao , Shaowen Wang , Jiashuo Sun , and Jiawei Han

In submission to ARR Oct, 2026

TL;DR arXiv Code Hugging Face

TL;DR: Retrieving agent memories by similarity is not enough; we train a memory composer with reinforcement learning to jointly select and order an LLM agent’s past experiences, improving task success with fewer memory tokens.
CaseMem: Closing the Loop from Agent Outcomes to Memory Reuse

Xinyi Fan , Yixuan Xie, Xing Fan , Chenlei Guo , Jie Hao , and Jiawei Han

In submission to ICLR, 2027
Ask to Distill: Learning to Synthesize Data for On-Policy Distillation

Jiashuo Sun , Hao Zhang , Xueqiang Xu , Heng Wang , Yixuan Xie, Pengcheng Jiang , Zhenrui Yue , Jiajun Fan , Peiran Li , Ge Liu , Shaowen Wang , and Jiawei Han

Code Hugging Face
Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation

Jiashuo Sun^† , Jimeng Shi^† , Yixuan Xie, Saizhuo Wang , Jash Rajesh Parekh , Pengcheng Jiang , Zhiyi Shi , Jiajun Fan , Qinglong Zheng , Peiran Li , Shaowen Wang , Ge Liu , and Jiawei Han

TL;DR arXiv Project Page Code

TL;DR: PyRAG reformulates multi-hop RAG as executable Python programs over retrieve/answer tools, with compiler-grounded self-repair and adaptive retrieval—outperforming strong baselines on five QA benchmarks (up to +25.5 EM on Bamboogle).
TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation

Jiashuo Sun^† , Yixuan Xie^†, Jimeng Shi , Shaowen Wang , and Jiawei Han

TL;DR arXiv

TL;DR: We propose TaSR-RAG, which uses a lightweight two-level taxonomy to guide step-wise triple-based evidence selection for multi-hop RAG, outperforming strong baselines by up to 14%.