发表论文（Publications）

1. Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning

基本信息

作者

Jiaqi Liu, Kaiwen Xiong, Peng Xia, Yiyang Zhou, Haonian Ji, Lu Feng, Siwei Han, Mingyu Ding, Huaxiu Yao

Teaser 图

images/Agent0-vl.png（已复制至本文件夹 images/ 目录）

引用格式

Jiaqi Liu, Kaiwen Xiong, Peng Xia, Yiyang Zhou, Haonian Ji, Lu Feng, Siwei Han, Mingyu Ding, Huaxiu Yao, “Agent0-vl: Exploring self-evolving agent for tool-integrated vision-language reasoning,” 2025. [Online]. Available: https://arxiv.org/abs/2511.19900

BibTeX

@misc{liu2025agent0vlexploringselfevolvingagent,
      title={Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning},
      author={Jiaqi Liu and Kaiwen Xiong and Peng Xia and Yiyang Zhou and Haonian Ji and Lu Feng and Siwei Han and Mingyu Ding and Huaxiu Yao},
      year={2025},
      eprint={2511.19900},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2511.19900},
}

2. Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails

基本信息

作者

Siwei Han, Kaiwen Xiong, Jiaqi Liu, Xinyu Ye, Yaofeng Su, Wenbo Duan, Xinyuan Liu, Cihang Xie, Mohit Bansal, Mingyu Ding, Linjun Zhang, Huaxiu Yao

其中 Siwei Han 和 Kaiwen Xiong 是 equal contribution

摘要

We identify the Alignment Tipping Process, a critical post-deployment risk unique to self-evolving LLM agents. We formalize and analyze Alignment Tipping Process through two complementary paradigms: Self-Interested Exploration, where repeated high-reward deviations induce individual behavioral drift, and Imitative Strategy Diffusion, where deviant behaviors spread across multi-agent systems

Teaser 图

images/ATP.png

引用格式

Siwei Han, Kaiwen Xiong, Jiaqi Liu, Xinyu Ye, Yaofeng Su, Wenbo Duan, Xinyuan Liu, Cihang Xie, Mohit Bansal, Mingyu Ding, Linjun Zhang, Huaxiu Yao, “Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails,” 2026. [Online]. Available: https://arxiv.org/abs/2510.04860v2

BibTeX

@misc{han2026alignmenttippingprocessselfevolution,
      title={Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails}, 
      author={Siwei Han and Kaiwen Xiong and Jiaqi Liu and Xinyu Ye and Yaofeng Su and Wenbo Duan and Xinyuan Liu and Cihang Xie and Mohit Bansal and Mingyu Ding and Linjun Zhang and Huaxiu Yao},
      year={2026},
      eprint={2510.04860},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2510.04860}, 
}

3. An Adaptive Sliding Window Estimator for Positioning of Unmanned Aerial Vehicle Using a Single Anchor

基本信息

作者

Kaiwen Xiong, Sijia Chen, Wei Dong

摘要

We propose an adaptive sliding window estimator equipped with an estimation reliability evaluator, where the states, noise covariance matrices, and aerial drag are estimated simultaneously.

关键词

Adaptive noise covariance, aerial drag estimation, position estimation, single anchor

Teaser 图

images/RASWE_graphical_abstract.png（已复制至本文件夹 images/ 目录）

引用格式

Kaiwen Xiong, Sijia Chen, Wei Dong, “An Adaptive Sliding Window Estimator for Positioning of Uncrewed Aerial Vehicle Using a Single Anchor,” in IEEE Sensors Journal, vol. 25, no. 16, pp. 30799-30809, 15 Aug. 2025, doi: 10.1109/JSEN.2025.3582282.

BibTeX

@ARTICLE{11063464,
  author={Xiong, Kaiwen and Chen, Sijia and Dong, Wei},
  journal={IEEE Sensors Journal},
  title={An Adaptive Sliding Window Estimator for Positioning of Uncrewed Aerial Vehicle Using a Single Anchor},
  year={2025},
  volume={25},
  number={16},
  pages={30799-30809},
  keywords={Sensors;Covariance matrices;Estimation;Interference;Noise;Kalman filters;Autonomous aerial vehicles;Vehicle dynamics;Sensor systems;Indexes;Adaptive noise covariance;aerial drag estimation;position estimation;single anchor},
  doi={10.1109/JSEN.2025.3582282}
}