I’m currently a first-year CS Ph.D. student at Nanyang Technological University (NTU).
Previously, I earned my B.Eng. from Tianjin University and M.Eng. from Tsinghua University.
My early research primarily focused on Graph Data Mining, and you can find some of my representative works here:
📂 Early Research Projects
-
⭐️ TFE-GNN (WWW 2023)
TFE-GNN: A Temporal Fusion Encoder Using Graph Neural Networks for Fine-grained Encrypted Traffic Classification -
⭐️ TGSL (CIKM 2023)
Time-aware Graph Structure Learning via Sequence Prediction on Temporal Graphs -
⭐️ MH-Net (AAAI 2025)
Revolutionizing Encrypted Traffic Classification with MH-Net: A Multi-View Heterogeneous Graph Model
🔍 Currently, I am interested in memory and experience in long-horizon agentic systems, with the goal of enabling agents to continuously learn, adapt, and evolve through interaction. My work explores how experience can be structured, reused, and refined over time, supported by adaptive computation and structured representations. Some of my recent works include:
-
⭐️ Graph of Records (ACL 2025 Main)
Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs -
⭐️ Router-R1 (NeurIPS 2025)
Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning -
⭐️ LLMRouter
LLMRouter: An Open-Source Library for LLM Routing -
⭐️ MemSkill
MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
🔗 You can find more about me on my Homepage.
📬 Feel free to reach out via wazhz14@gmail.com — I'm always open to discussion and collaboration!