About Me

I am a Ph.D. student in the Knowledge Engineering Group (KEG), Department of Computer Science and Technology, Tsinghua University, advised by Prof. Juanzi Li. Before starting my Ph.D. in 2025, I received my M.S. in Computer Science and Technology from Tsinghua University (2023-2025), and my dual bachelor’s degrees in Information Management and Information Systems and Software Engineering from Tsinghua University (2019-2023).

My research focuses on large language models, with particular interests in LLM agents for complex tasks and LLM alignment and mechanistic understanding. I am also the founder and lead of the Auto-Research Agents project at Zhipu AI (Z.AI), where I work on agent systems for automated research and on improving foundation models for frontier research workflows.

I have published 2 first-author papers and 5 co-authored papers at top venues in natural language processing and machine learning, with 280+ Google Scholar citations. You can find my publications on Google Scholar.

Detailed Research Interests

My recent work centers on two directions:

1) LLM agents for complex tasks
Developing LLM-based agents that combine retrieval-augmented generation (RAG), multi-agent collaboration, and reinforcement learning for complex tasks such as agentic search, scientific research, and financial decision-making.

2) LLM alignment and mechanistic understanding
Studying the capability boundaries and internal mechanisms of LLMs.

Selected Publications

1. AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
   Amy Xin*, Jinxin Liu*, Zijun Yao, Zhicheng Lee, Shulin Cao, Lei Hou, Juanzi Li
   KDD, 2025. Oral Presentation

2. LLMAEL: Large Language Models are Good Context Augmenters for Entity Linking
   Amy Xin*, Yunjia Qi*, Zijun Yao, Fangwei Zhu, Kaisheng Zeng, Bin Xu, Lei Hou, Juanzi Li
   CIKM, 2025. Oral Presentation

3. StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?
   Yanxu Chen*, Zijun Yao*, Yantao Liu*, Amy Xin, Jin Ye, Jianing Yu, Lei Hou, Juanzi Li
   arXiv preprint, 2025.

4. VisKoP: Visual Knowledge Oriented Programming for Interactive Knowledge Base Question Answering
   Zijun Yao*, Yuanyong Chen*, Xin Lv, Shulin Cao, Amy Xin, Jifan Yu, Hailong Jin, Jianjun Xu, Peng Zhang, Lei Hou, Juanzi Li
   ACL, 2023. Best Demo Award

5. AgentIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
   Yunjia Qi*, Hao Peng*, Xiaozhi Wang, Amy Xin, Youfeng Liu, Bin Xu, Lei Hou, Juanzi Li
   NeurIPS, 2025. Spotlight

6. How do Transformers Learn Implicit Reasoning?
   Jiaran Ye*, Zijun Yao*, Zhidian Huang, Liangming Pan, Jinxin Liu, Yushi Bai, Amy Xin, Weichuan Liu, Xiaoyin Che, Lei Hou, Juanzi Li
   NeurIPS, 2025. Spotlight

7. KoLA: Carefully Benchmarking World Knowledge of Large Language Models
   Jifan Yu*, Xiaozhi Wang*, Shangqing Tu, Shulin Cao, Daniel Zhang-Li, Xin Lv, Hao Peng, Zijun Yao, Xiaohan Zhang, Hanming Li, Chunyang Li, Zheyuan Zhang, Yushi Bai, Yantao Liu, Amy Xin, …, Lei Hou, Zhiyuan Liu, Bin Xu, Jie Tang, Juanzi Li
   ICLR, 2024.

^{* Equal contribution}

Honors and Activities

• ACL Best Demo Award (2023) for VisKoP.
• Tsinghua University Merit Scholarships (2021-2023), awarded three times.
• Active in research leadership and service within KEG, and involved in music and athletics communities at Tsinghua.

Beyond Research

Outside research, music is a big part of my life. I enjoy music arrangement, singing, and songwriting. I have long been active in music communities at Tsinghua.

I also have a soft spot for puppies and all kinds of cute animals - they reliably make my day better. Nya~

Last updated: Apr 2026.