Kaiming Liu

@misc{tigan2026,
  title = {Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents},
  author = {Kaiming Liu and Yuxuan Liu and Jinrui Ju and Minyuan Ruan and Xuanyu Lei and Peng Li and Yang Liu},
  year = {2026},
  eprint = {2610.17757},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.17757}
}

@misc{ioa2026,
  title = {Illusion of Alignment: Detecting Hidden Disagreement in Collaborative Dialogue},
  author = {Kaiming Liu and Fuwen Luo and Ziyue Wang and Jinrui Ju and Yuxuan Liu and Xuanyu Lei and Yunghwei Lai and Peng Li and Yang Liu},
  year = {2026},
  eprint = {2608.08210},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.08210}
}

@misc{align2025,
  title = {Agent-Environment Alignment via Automated Interface Generation},
  author = {Kaiming Liu and Xuanyu Lei and Ziyue Wang and Peng Li and Yang Liu},
  year = {2025},
  eprint = {2505.21055},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.21055}
}

@misc{aigs2024,
  title = {AIGS: Generating Science from AI-Powered Automated Falsification},
  author = {Zijun Liu and Kaiming Liu and Yiqi Zhu and Xuanyu Lei and Zonghan Yang and Zhenhe Zhang and Peng Li and Yang Liu},
  year = {2024},
  eprint = {2411.11910},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.11910}
}