Xun Wang汪洵

Third-year Ph.D. student @ IIIS, Tsinghua.

Hi, I am Xun Wang!

I am currently a third-year Ph.D. student at Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University, where I am fortunate to be advised by Prof. Longbo Huang. Prior to this, I earned a Bachelor of Science degree in 2024 from the School of Computer Science at Nanjing University.

Research Interests

My research interests broadly lie in AI for decision-making, focusing on the algorithms and applications of Reinforcement Learning (RL), Large Language Models (LLMs), and their intersection. Currently, I am studying how to leverage frontier models and architectures to achieve reliable and efficient decision-making in complex settings.

News

  • [2026.05] Four papers on RL and GFlowNets accepted to ICML 2026!
  • [2026.02] Paper “OM²P: Offline Multi-Agent Mean-Flow Policy” accepted to AAMAS 2026!
  • [2025.07] Paper “Beyond Static Populations: Efficient Delay-Constrained Scheduling for Dynamic Users via Deep Reinforcement Learning” accepted to MobiHoc 2025!
  • [2025.07] Paper “Online Adaptable Offline RL with Guidance Model” accepted to TNNLS!

Preprints

arXiv2026
FlexLoop: Depth-Elastic Looped Policies for Adaptive Test-Time Computation in Deep RL
Xun Wang, Ruishuo Chen, Yu Chen, Zhuoran Li, Longbo Huang
arXiv preprint arXiv:2609.34488, Sept. 2026.
arXiv2026
When Context Returns: Toward Robust Internalization in On-Policy Distillation
Xun Wang, Ruishuo Chen, Zhuoran Li, Yu Chen, Longbo Huang
arXiv preprint arXiv:2606.11627, June 2026.
arXiv2025
From Solo to Symphony: Orchestrating Multi-Agent Collaboration with Single-Agent Demos
Xun Wang, Zhuoran Li, Yanshan Lin, Hai Zhong, Longbo Huang
arXiv preprint arXiv:2511.02762, Nov. 2025.
arXiv2026
The Router Within: Eliciting Native Skill Routing from a Frozen LLM
Ruishuo Chen, Xun Wang, Yu Chen, Zhuoran Li, Longbo Huang
arXiv preprint arXiv:2609.15982, Sept. 2026.
arXiv2026
Optimal Skill Selection for LLM Agents with Provable Bicriteria Guarantees
Yu Chen, Ruishuo Chen, Xun Wang, Zhuoran Li, Longbo Huang
arXiv preprint arXiv:2608.19993, Aug. 2026.
arXiv2026
MLREF: Efficient Module Reuse for Reward Design in Reinforcement Learning via Large Language Models
Chenglin Liu, Xun Wang, Ruishuo Chen, Zhuoran Li, Longbo Huang
arXiv preprint arXiv:2608.18827, Aug. 2026.

Selected Publications

* indicates equal contribution ConferenceJournal

ICML2026
Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training
Ruishuo Chen, Xun Wang, Rui Hu, Zhuoran Li, Longbo Huang
Proceedings of Forty-third International Conference on Machine Learning, July 2026.
ICML2026
Reparameterization Proximal Policy Optimization
Hai Zhong, Xun Wang, Zhuoran Li, Longbo Huang
Proceedings of Forty-third International Conference on Machine Learning, July 2026.
ICML2026
Reparameterization Flow Policy Optimization
Hai Zhong, Zhuoran Li, Xun Wang, Longbo Huang
Proceedings of Forty-third International Conference on Machine Learning, July 2026.
ICML2026
Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies
Zhuoran Li, Hai Zhong, Xun Wang, Qingxin Xia, Lihua Zhang, Longbo Huang
Proceedings of Forty-third International Conference on Machine Learning, July 2026.
QCNC2026
Effective Entanglement Scheduling in Quantum Networks via Deep Reinforcement Learning
Xun Wang, Longbo Huang, John C.S. Lui
Proceedings of International Conference on Quantum Communications, Networking, and Computing, Apr. 2026. Oral Invited Paper
MobiHoc2025
Beyond Static Populations: Efficient Delay-Constrained Scheduling for Dynamic Users via Deep Reinforcement Learning
Xun Wang*, Zhuoran Li*, Longbo Huang
The 26th International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing, Oct. 2025. Oral
TNNLS2025
Online Adaptable Offline RL with Guidance Model
Xun Wang, Jingmian Wang, Zhuzhong Qian and Bolei Zhang
IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 11, pp. 19762-19774, Nov. 2025.
ECAI2023
SDV: Simple Double Validation Model-based Offline Reinforcement Learning
Xun Wang, Haonan Chen, Junming Yang, Zhuzhong Qian and Bolei Zhang
Proceedings of 26th European Conference on Artificial Intelligence, Sept. 2023. Oral

More publications →