Yixuan Xie 「谢沂烜」

Hi, this is Mark!

I am an incoming 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 current research interests include:

Retrieval-augmented generation (RAG);
Search agents and agent memory;
Reinforcement learning for agentic reasoning.

I am open to fall 2026 internships in RAG / Search Agents/ Agentic RL — feel free to reach out.

News

May 26, 2026	Started as a summer RA on memory for search agents, in collaboration with researchers at Amazon.
Apr 01, 2026	Continuing at UIUC for MSCS, advised by Prof. Jiawei Han.

Publications

Preprint

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).
Preprint

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%.