Xuchuang Wang
multi-agent learning & quantum networking
I am a postdoctoral researcher 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 also interned at Theory Center, Microsoft Research Asia, mentored by Wei Chen. I obtained my B.Eng. with Hons. from Xi’an Jiaotong University.
My research centers on online learning (theory, also known as sequential decision-making under uncertainty) and quantum networking (application). I develop rigorous algorithms for multi-agent online learning, with a focus on efficient communications, heterogeneous agents, and realistic feedback. I also devise practical algorithms for quantum networks, with a focus on routing (optimization) and network tomography (evaluation).
I am on the 2025-2026 job market looking for full-time academia positions. Please feel free to reach out!
research highlights
- multi-agent sequential decision-making:
- communication-efficient algorithms (SIGMETRICS’25, NeurIPS’25, ICLR’23, AISTATS’23),
- heterogenous cooperation algorithms (SIGMETRICS’26, AAAI’25a, UAI’25, UAI’23),
- agents with grouping or shareable policies (Ski-Rental Preprint, ICML’22, IJCAI’22).
- quantum network optimization and evaluation:
- quantum network routing optimization (INFOCOM’25, INFOCOM’24),
- quantum best arm identification (AAAI’25b),
- quantum network tomography (Mergecast Preprint, OPAL Preprint).
- online learning with realistic feedback:
- strong-adversary manipulated feedback (ICLR’25, L4DC’25),
- fusing absolute and relative feedback (ICML’25),
- multi-fidelity feedback (NeurIPS’23).
news
| Dec 03, 2025 | I’ll be attending NeurIPS 2025 from Wednesday 3 December to Sunday 7 December 2025 in San Diego, CA. Looking forward to seeing you there! |
|---|---|
| Nov 08, 2025 | One paper on multi-agent conversational bandits for LLM responses alignment is accepted by AAAI 2026, AI alignment track. |
| Oct 29, 2025 | I give an invited talk on Asynchronous Decision-Making in Multi-Agent Bandits in INFORMS Annual Meeting 2025, Atlanta, GA. |
| Sep 26, 2025 | One paper on heterogeneous multi-agent learning is accepted by SIGMETRICS 2026. |
| Sep 19, 2025 | One paper on multi-agent communication-efficient algorithm is accepted by NeurIPS 2025. |