Publications

Preprints

• Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift
  Bochao Li, Yao Fu, Wei Chen, Fang Kong#.
  ICML 2026 Workshop on Decision-Making from Offline Datasets to Online Adaptation: Black-Box Optimization to Reinforcement Learning

• A Unified Algorithmic Framework for Hybrid Reinforcement Learning in Tabular MDPs with Shifted Transition Dynamics
  Zheshun Wu, Renjie Zheng, Jinhang Zuo, Zenglin Xu, Fang Kong#.
  arXiv preprint, 2026

• Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?
  Minghan Wang, Boyuan Wang, Jinhang Zuo, Yuxin Tao, Fang Kong#.
  arXiv preprint, 2026

• Harnesses for Inference-Time Alignment over Execution Trajectories
  Boyuan Wang, Bochao Li, Minghan Wang, Yuxin Tao, Fang Kong#.
  arXiv preprint, 2026

Publications

• Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback
  Qirun Zeng, Xuchuang Wang, Jiayi Shen, Xutong Liu, Fang Kong, Jinhang Zuo
  Accepted by NeurIPS, 2026

• Anytime-Valid Multi-Objective Online Experimentation with Contrast Certificates
  Zilong Wang, Penglei Zhao, Fang Kong, Yong Wang, Shuai Li.
  Accepted by CIKM, 2026

• Hybrid Combinatorial Multi-armed Bandits with Probabilistically Triggered Arms
  Kongchang Zhou, Tingyu Zhang, Wei Chen, Fang Kong#.
  Transactions on Machine Learning Research (TMLR), 2026

• CES: Combinatorial Experts Selection via Contextual Linear Bandits
  Jinkun Xu, Minghan Wang, Zhiyong Wang, Zhongxiang Dai, Fang Kong#.
  Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Research Track), 2026

• Federated Combinatorial Causal Bandits with Heterogeneous Causal Influences
  Zheshun Wu, Wei Chen, Zenglin Xu, Fang Kong#.
  Proceedings of the 42nd Annual Conference on Uncertainty in Artificial Intelligence (UAI), 2026

• Bandit learning in matching markets with relative feedback
  Fang Kong, Xiaoxi Zhang, Xiao Huang, Lijun Zhang, Shuai Li.
  Theoretical Computer Science, 2026

• Bandit Learning in Matching Markets Robust to Adversarial Corruptions
  Zheshun Wu, Jinhang Zuo, Zenglin Xu, Fang Kong#.
  The 14th International Conference on Learning Representations (ICLR), 2026

• Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution
  Manhin Poon, Xiangxiang Dai, Xutong Liu, Fang Kong, John C.S. Lui, Jinhang Zuo.
  Proceedings of the 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026

• Learning Across the Gap: Hybrid Multi-armed Bandits with Heterogeneous Offline and Online Data
  Qijia He, Minghan Wang, Xutong Liu, Zhiyong Wang, Fang Kong#.
  Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS), 2025

• A Survey on Bandit Learning in Matching Markets
  Shuai Li, Zilong Wang, Fang Kong.
  Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI) Survey Track, 2025

• Bandit Learning in Matching Markets with Indifference
  Fang Kong, Jingqi Tang, Mingzhu Li, Pinyan Lu, John C.S. Lui, Shuai Li.
  Proceedings of the 13th International Conference on Learning Representations (ICLR), 2025

• Improved Analysis for Bandit Learning in Matching Markets
  Fang Kong, Zilong Wang and Shuai Li.
  Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS), 2024

• Sequential Optimum Test with Multi-armed Bandits for Online Experimentation
  Fang Kong, Penglei Zhao, Shichao Han, Yong Wang and Shuai Li.
  Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM, Applied Research Paper Track), 2024

• Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits [arXiv]
  Yu Xia*, Fang Kong*, Tong Yu, Liya Guo, Ryan A. Rossi, Sungchul Kim and Shuai Li.
  The Web Conference (WWW), 2024

• Improved Bandits in Many-to-one Matching Markets with Incentive Compatibility [arXiv]
  Fang Kong and Shuai Li.
  Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024

• Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization
  Fang Kong*, Xiangcheng Zhang*, Baoxiang Wang and Shuai Li.
  Transactions on Machine Learning Research (TMLR), 2024
  Also invited as a poster presentation at ICLR, 2025

• Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader Algorithm [arXiv]
  Fang Kong, Canzhe Zhao and Shuai Li.
  Proceedings of 36th Conference on Learning Theory (COLT), 2023

• Online Influence Maximization under Decreasing Cascade Model [arXiv]
  Fang Kong, Jize Xie, Baoxiang Wang, Tao Yao and Shuai Li.
  Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023

• Stochastic No-Regret Learning for General Games with Variance Reduction [arXiv]
  Yichi Zhou, Fang Kong and Shuai Li.
  Proceedings of the 11th International Conference on Learning Representations (ICLR), 2023

• Player-optimal Stable Regret for Bandit Learning in Matching Markets [arXiv][slides]
  Fang Kong and Shuai Li.
  Proceedings of the 34th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2023  

• Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback [arXiv] [slides]
  Fang Kong, Yichi Zhou and Shuai Li.
  Proceedings of the 39th International Conference on Machine Learning (ICML), 2022  

• Thompson Sampling for Bandit Learning in Matching Markets [arXiv]
  Fang Kong, Junming Yin and Shuai Li.
  Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI), 2022

• The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle [arXiv] [slides] [poster]
  Fang Kong, Yueran Yang, Wei Chen and Shuai Li.
  Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), 2021

• Combinatorial Online Learning based on Optimizing Feedbacks
  Fang Kong, Yueran Yang, Wei Chen and Shuai Li.
  Big Data Research, 2021

• Online Influence Maximization under Linear Threshold Model[arXiv][slides][poster]
  Shuai Li, Fang Kong, Kejie Tang, Qizhi Li and Wei Chen.
  Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS), 2020

• A Survey on Online Influence Maximization
  Fang Kong, Qizhi Li and Shuai Li.
  Computer Science, 2020