Haolong Chen, 陈 浩泷

Haolong Chen, 陈 浩泷

PhD student at CUHK, Shenzhen. Interested in Artificial Intelligence, Music, Films.

Haolong Chen

About Me

I am currently pursuing my Ph.D. in Computer and Information Engineering at The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen) under the supervision of Prof. Guangxu Zhu and Prof. Tsung-Hui Chang. I received my B.Eng. in Software Engineering from Jinan University in 2023.

My research lies at the intersection of LLM agents and domain-specific intelligence, with a particular focus on self-evolving agents, agent memory systems, and efficient training methods. I have published 5 papers in CCF-A-ranked conferences and journals.

I serve as a conference reviewer for ICASSP, WCNC, ICC, GLOBECOM, ICCC, and PIMRC, and as a journal reviewer for TMC.

I am passionate about developing LLM agents that can continuously evolve while remaining efficient and reliable. I am always open to research collaborations and discussions.

News

  • [Aug. 2026] Our paper “ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval” is now available on arXiv.
  • [Aug. 2026] Our paper “Error-Aware Reverse Auction Mechanism for Large Language Model Routing” is now available on arXiv.
  • [Jun. 2026] ✅ Our paper “DK-Root: A Joint Data-and-Knowledge-Driven Framework for Root Cause Analysis of QoE Degradations in Mobile Networks” has been accepted by IEEE Transactions on Networking!
  • [Jun. 2026] Our paper “QoEReasoner: An Agentic Reasoning Framework for Automated and Explainable QoE Diagnosis in RANs” is now available on arXiv.
  • [May. 2026] ✅ Our paper “STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction” has been accepted by SIGKDD 2026!
  • [May. 2026] ✅ Our paper “AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments” has been accepted by ICML 2026!
  • [Apr. 2026] Our paper “Three Birds, One Stone: Solving the Communication-Memory-Privacy Trilemma in LLM Fine-tuning Over Wireless Networks with Zeroth-Order Optimization” is now available on arXiv.
  • [Mar. 2026] ✅ Our paper “FeedSign: Robust Full-parameter Federated Fine-tuning of Large Models with Extremely Low Communication Overhead of One Bit” has been accepted by IEEE Transactions on Mobile Computing!
  • [Jun. 2025] ✅ Our paper “An overview of domain-specific foundation model: key technologies, applications and challenges”, has been accepted by SCIENCE CHINA Information Sciences!