Yibo Miao

Yibo Miao

Researcher at RL Team, Moonshot

Yibo Miao(θ‹—δΉ‰εš) is now a researcher at Moonshot, working on the foundational Large Language Models (LLMs). Yibo earned his Master’s degree at Shanghai Jiao Tong University in 2025, where he was fortunate to be advised by Prof. Zhijie Deng. Before that, he received his Bachelor's degree at Huazhong University of Science and Technology in 2022.

His research interests lie in large language models and coding agent.

πŸ“ Preprints

  • Kimi K2.5: Visual Agentic Intelligence [Paper]
    Yibo Miao (Co-author), contributed to Coding Agentic Capabilities for Kimi K2.5

  • Kimi k2: Open agentic intelligence [Paper]
    Yibo Miao (Co-author), contributed to Coding Agentic Capabilities for Kimi K2

  • Kimi-vl technical report [Paper]
    Yibo Miao (Co-author), contributed to Coding Capabilities for Kimi-vl

  • Qwen2.5 technical report [Paper]
    Yibo Miao (Co-author), contributed to Coding Capabilities for Qwen models

  • Qwen2.5-coder technical report [Paper]
    Yibo Miao (Co-author)

πŸ“ Selected Publications

* indicates equal contribution.

2026

  • Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents [Paper]
    Zonghan Yang, Shengjie Wang, Kelin Fu, Wenyang He, Weimin Xiong, Yibo Liu, Yibo Miao, Bofei Gao, Yejie Wang, Yingwei Ma, Yanhao Li, Yue Liu, Zhenxing Hu, Kaitai Zhang, Shuyi Wang, Huarong Chen, Flood Sung, Yang Liu, Yang Gao, Zhilin Yang, Tianyu Liu

2025

  • CodeArena: Evaluating and Aligning CodeLLMs on Human Preference [Paper]
    Jian Yang, Jiaxi Yang, Wei Zhang, Jin Ke, Yibo Miao, Lei Zhang, Liqun Yang, Zeyu Cui, Yichang Zhang, Zhoujun Li, Binyuan Hui, Junyang Lin.
    ACL 2025

  • Towards a better initial policy model for scalable long-cot reinforcement learning [Paper]
    Bofei Gao, Yejie Wang, Yibo Miao, Ruoyu Wu, Feifan Song, Longhui Yu, Tianyu Liu, Baobao Chang.
    Findings of ACL 2025.

  • Qwen2. 5-xCoder: Multi-Agent Collaboration for Multilingual Code Instruction Tuning [Paper]
    Jian Yang, Wei Zhang, Yibo Miao, Shanghaoran Quan, Zhenhe Wu, Qiyao Peng, Liqun Yang, Tianyu Liu, Zeyu Cui, Binyuan Hui, Junyang Lin.
    ACL 2025

  • 3D-Properties: Identifying Challenges in DPO and Charting a Path Forward [Paper]
    Yuzi Yan*, Yibo Miao*, Jialian Li, Yipin Zhang, Jian Xie, Zhijie Deng, Dong Yan.
    ICLR 2025

  • Omni-math: A universal olympiad level mathematic benchmark for large language models [Paper]
    Bofei Gao, Feifan Song, Zhe Yang, Zefan Cai, Yibo Miao, Qingxiu Dong, Lei Li, Chenghao Ma, Liang Chen, Runxin Xu, Zhengyang Tang, Benyou Wang, Daoguang Zan, Shanghaoran Quan, Ge Zhang, Lei Sha, Yichang Zhang, Xuancheng Ren, Tianyu Liu, Baobao Chang.
    ICLR 2025

2024

  • AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models [Paper]
    Zihao Zeng*, Yibo Miao*, Hongcheng Gao, Hao Zhang, Zhijie Deng.
    Findings of EMNLP 2024.

  • Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model [Paper]
    Yibo Miao*, Hongcheng Gao*, Hao Zhang, Zhijie Deng.
    Findings of ACL 2024.

  • Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method [Paper]
    Tian Xia, Zhiwei He, Tong Ren, Yibo Miao, Zhuosheng Zhang, Yang Yang, Rui Wang.
    Findings of ACL 2024.

  • Bayesian Exploration of Pre-trained Models for Low-shot Image Classification [Paper]
    Yibo Miao, Yu Lei, Feng Zhou, Zhijie Deng.
    CVPR 2024

πŸ“– Education

  • 2022.09 - 2025.03, M.E. at Shanghai Jiao Tong University.
  • 2018.09 - 2022.06, B.E. at Huazhong University of Science and Technology.

πŸ“– Experiences

  • 2025.1 - present, Researcher at RL Team, Moonshot.
  • 2024.7 - 2025.1, Intern at Qwen, Alibaba.
  • 2024.2 - 2024.7, Intern at RL Team, Baichuan.
  • 2023.7 - 2023.12, Intern at SenseTime Research.