Publications

2026

1. 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).

2. 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%.