publications

2026

1. ICLR

   

   Empowering multi-robot cooperation via sequential world models

   Z. Zhao, Honglei Guo, S. Chen, and 4 more authors

   In International Conference on Learning Representations, 2026

   Bib

   

   @inproceedings{guo2026multirobot,
     title = {Empowering multi-robot cooperation via sequential world models},
     author = {Zhao, Z. and Guo, Honglei and Chen, S. and Xu, K. and Jiang, B. and Zhu, Y. and Zhao, D.},
     booktitle = {International Conference on Learning Representations},
     year = {2026},
     pages = {13262--13280},
   }

2. arXiv

   

   Learning Long-Term Educational Investment Policies under Residential Sorting

   Honglei Guo, Shuo Chen, Mingjie Bi, and 3 more authors

   2026

   arXiv preprint arXiv:2608.07295

   Abs arXiv Bib

   

   Allocating public-school investment effectively and fairly is difficult when school access depends on residence. School improvements can raise nearby housing demand and prices, reshape enrollment, and potentially limit access for lower-income households. These effects evolve as residential sorting changes school composition, quality, and future investment needs. We address this gap with a dynamic multi-agent framework that links government investment, household sorting, housing prices, population turnover, enrollment, and evolving school quality. A government planner uses reinforcement learning to identify multiyear allocation policies that account for household responses while balancing aggregate educational access and equity.

   @misc{guo2026education,
     title = {Learning Long-Term Educational Investment Policies under Residential Sorting},
     author = {Guo, Honglei and Chen, Shuo and Bi, Mingjie and Sun, Zeyang and Wang, Xiaoxi and Zhao, Yuhan},
     year = {2026},
     note = {arXiv preprint arXiv:2608.07295},
   }

3. arXiv

   

   OpFlow: Learning Opportunity-Conditioned Choice Potentials for Robust OD Flow Prediction

   Changjian Liu, Yong Gao, Yuqing Wang, and 5 more authors

   2026

   arXiv preprint arXiv:2607.03200

   Abs arXiv Bib

   

   Origin-destination (OD) flow prediction is central to urban analytics, yet deep models trained on raw counts remain vulnerable to distribution shift. The core problem is that raw count supervision cannot distinguish transferable choice mechanisms from environment-specific shortcuts. We propose OpFlow, a mechanism-constrained framework that learns row-centered choice potentials and reconstructs flows by combining the induced allocation with a separately calibrated origin scale. Controlled synthetic shifts and real-world experiments show that OpFlow improves robustness under environment shifts.

   @misc{guo2026opflow,
     title = {OpFlow: Learning Opportunity-Conditioned Choice Potentials for Robust OD Flow Prediction},
     author = {Liu, Changjian and Gao, Yong and Wang, Yuqing and Su, Leyi and Guo, Honglei and Wang, Zhiyang and Wang, Xiaoyu and Zhang, Fan},
     year = {2026},
     note = {arXiv preprint arXiv:2607.03200},
   }

4. arXiv

   

   Hierarchical Multiagent Reinforcement Learning for Multi-Group Tax Game

   Honglei Guo, Yuhan Zhao, and Yexin Li

   2026

   arXiv preprint arXiv:2605.04741

   Abs arXiv Bib

   

   Reinforcement learning has increasingly been applied to economic decision-making, including taxation, public spending, and labor supply. However, existing models typically consider only a single government-household group, overlooking strategic interactions among competing governments. We formulate taxation as a hierarchical multi-group game and propose a bilevel multi-agent reinforcement learning framework with curriculum learning and a closed-loop sequential update mechanism to improve training stability and convergence. Experiments show that the proposed method learns stable and sustainable tax policies under inter-group competition.

   @misc{guo2026taxgame,
     title = {Hierarchical Multiagent Reinforcement Learning for Multi-Group Tax Game},
     author = {Guo, Honglei and Zhao, Yuhan and Li, Yexin},
     year = {2026},
     note = {arXiv preprint arXiv:2605.04741},
   }

5. ECMX

   

   High precision prediction of time-varying photovoltaic power based on dynamic adjacency matrix and temporal spectral graph convolution network

   Honglei Guo, Z. Su, Z. Wang, and 3 more authors

   Energy Conversion and Management: X, 2026

   Bib

   

   @article{guo2026energyx,
     title = {High precision prediction of time-varying photovoltaic power based on dynamic adjacency matrix and temporal spectral graph convolution network},
     author = {Guo, Honglei and Su, Z. and Wang, Z. and Zhan, G. and Liu, C. and Bu, L.},
     journal = {Energy Conversion and Management: X},
     volume = {30},
     pages = {101676},
     year = {2026},
   }

2025

1. IROS

   

   EIC framework for hand exoskeletons based on a multimodal large language model

   H. Li, Z. Su, Honglei Guo, and 3 more authors

   In 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2025

   

2024

1. IJDE

   

   Integrating trajectory data and demographic characteristics: a trajectory semantic model for predicting travel flow and conducting interaction analysis

   C. Liu, S. Gong, H. Su, and 5 more authors

   International Journal of Digital Earth, 2024

   Bib

   

   @article{guo2024trajectory,
     title = {Integrating trajectory data and demographic characteristics: a trajectory semantic model for predicting travel flow and conducting interaction analysis},
     author = {Liu, C. and Gong, S. and Su, H. and Chen, J. and Guo, Honglei and He, J. and Jing, C. and Liu, Y.},
     journal = {International Journal of Digital Earth},
     volume = {17},
     number = {1},
     pages = {2392842},
     year = {2024},
   }

2. CAC

   

   Short-term photovoltaic power forecasting based on patch-Transformer model

   G. Zhan, Y. Ye, Honglei Guo, and 3 more authors

   In 2024 China Automation Congress (CAC), 2024