Xuchuang Wang

My research builds the algorithmic foundations of two emerging networks:

• quantum networking — networks that distribute qubits and entanglement across distant nodes to enable distributed quantum computing, quantum-enhanced sensing, and provably-secure communication;
• agentic networking — networks of AI/LLM agents that communicate, coordinate, and learn together to act in the world.

A single methodology runs through both: sequential decision-making under uncertainty (online learning, bandits, and reinforcement learning). I use it to design rigorous, communication-efficient, and provably-good algorithms that hold up under realistic, noisy, and even adversarial feedback.

I am a RGC Junior Research Fellow in the Department of Computer Science and Engineering at Chinese University of Hong Kong and an incoming Assistant Professor in the Department of Computer Science at Hong Kong Baptist University.

Prior to this, I was a postdoctoral researcher for three years in the Manning College of Information & Computer Science at University of Massachusetts Amherst, working with Don Towsley at ACQUIRE Lab and Mohammad Hajiesmaili at SOLAR Lab. I received my Ph.D. in the Department of Computer Science & Engineering at The Chinese University of Hong Kong under the guidance of John C.S. Lui at ANSR Lab. I obtained my B.Eng. with Hons. (now Qian Xuesen Honors College) from Xi’an Jiaotong University.

joining the lab

I am building a research group at HKBU CS at the intersection of learning theory and the two networks described above. Representative questions include:

• routing entanglement through a noisy quantum network, and verifying its health from limited measurements;
• enabling a population of LLM agents to share what they learn while keeping communication overhead low;
• establishing provable guarantees when feedback is adversarial, multi-modal, or quantum.

Students in my group publish at leading venues (NeurIPS, ICML, ICLR, AAAI, SIGMETRICS, INFOCOM) and collaborate with labs at UMass, CUHK, CityU, NJU, and SJTU; recent mentees and their first-author papers appear on the team page.

Beyond Ph.D. positions, I host Research Assistants (remote or onsite at HKBU) on 3- or 6-month terms — suitable for senior undergraduates, master’s students, or recent graduates who wish to gain research experience before applying to a Ph.D. program, or to develop a concrete project toward publication.

Ideal background: strong fundamentals in probability, optimization, or theoretical computer science. Prospective applicants should consult the openings page for research directions and application instructions.

research highlights

• quantum networking — algorithms for the quantum internet:
  • entanglement routing and resource optimization (INFOCOM’25, INFOCOM’24),
  • quantum network tomography and evaluation (Mergecast Preprint, QCNC’26),
  • quantum-enhanced sequential learning (AAAI’25b).
• agentic networking — learning algorithms for networked AI agents:
  • communication-efficient cooperation across agents (SIGMETRICS’25, NeurIPS’25, ICLR’23, AISTATS’23),
  • heterogeneous and asymmetric cooperation (SIGMETRICS’26, AAAI’25a, UAI’25, UAI’23),
  • scalable agent grouping and shareable policies (Ski-Rental Preprint, ICML’22, IJCAI’22),
  • aligning LLM agents from interactive feedback (AAAI’26).
• foundations — online learning with realistic feedback:
  • robustness to strong-adversary manipulated feedback (ICLR’25, L4DC’25),
  • fusing absolute and relative human feedback (ICML’25),
  • multi-fidelity feedback for sample-efficient learning (NeurIPS’23).