About Me

Hello, I’m Zhi Cheng, an Applied AI Engineer at Z.AI (Zhipu AI). My recent work focuses on Agent Harness development and enterprise agent applications, spanning multi-agent orchestration, tool integration, and execution feedback loops. I lead projects from technical design and implementation to customer POC validation, working with domain experts to translate business requirements into executable workflows.

My earlier research explored reasoning-enhanced retrieval-augmented generation (RAG) and neuro-symbolic reasoning for knowledge-based question answering (KBQA). I also have hands-on experience in constructing training data, applying supervised fine-tuning (SFT), and evaluating LLMs for complex question answering.

I earned my Master’s Degree in Computer Science and Technology from Tsinghua University in 2025, where I was a member of the KEG Lab, supervised by Prof. Juanzi Li. I received my bachelor’s degree in Automation from Shanghai Jiao Tong University.

Before my master’s studies, I worked as an AI Engineer at Wise AI Malaysia on face anti-spoofing and voice cloning. My earlier research explored semi-supervised learning and graph neural networks.

Publications

ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation
Jinxin Liu*, Zhicheng Lee*, Shulin Cao, Jiajie Zhang, Weichuan Liu, Xiaoyin Che, Lei Hou, Juanzi Li.
International Joint Conference on Neural Networks (IJCNN), 2026

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.
31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Vol. 2, 2025

DiaKoP: Dialogue-based Knowledge-oriented Programming for Neural-symbolic Knowledge Base Question Answering
Zhicheng Lee*, Zhidian Huang*, Zijun Yao, Jinxin Liu, Amy Xin, Lei Hou, Juanzi Li.
Conference on Information and Knowledge Management (CIKM demo track), 2024

Deep Semi-Supervised Learning via Dynamic Anchor Graph Embedding Learning
Zihao Wang, Enmei Tu, Zhicheng Lee
International Joint Conference on Neural Networks (IJCNN), 2021