Zhen Huang

Zhen Huang

I’m Zhen Huang (“黄臻” in Chinese), a first-year Ph.D. student at Fudan University, under the supervision of Pengfei Liu (affiliated with GAIR Lab @ SJTU). My current research interest is long-horizon agents. Previously, I also focused on data-centric AI, in particular curating high-quality data in a more automated way across various stages of pre-training, mid-training and post-training. I’m currently an intern at the Hunyuan LLM Agent Team, Tencent.

🔥 News

  • 2026.04:  🎉🎉 One paper accepted by ACL 2026 (main) on LLM Pretraining - “Unlocking the Value of Scientific Data for Pre-training”.

  • 2025.07:  🎉🎉 One paper accepted by COLM 2025 on LLM reasoning - “LIMO: Less is More for Reasoning”.

  • 2024.09:  🎉🎉 One paper accepted by NeurIPS 2024 on LLM&LMM evaluation - “OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI”.

📝 Publications

( * : equal contribution, † : corresponding author )

( * : equal contribution, † : corresponding author )

  • DaVinci-Dev: Agent-native Mid-training for Software Engineering

    Ji Zeng, Dayuan Fu, Tiantian Mi, Yumin Zhuang, Yaxing Huang, Xuefeng Li, Lyumanshan Ye, Muhang Xie, Qishuo Hua, Zhen Huang, Mohan Jiang, Hanning Wang, Jifan Lin, Yang Xiao, Jie Sun, Yunze Wu, Pengfei Liu†

    ICML 2026 (Oral)

    [Paper][Code][🤗 Dataset][🤗 Model (32B)][🤗 Model (72B)]

  • SciPedia: Unlocking the Value of Scientific Data for Pre-training

    Yiwei Qin*, Zhen Huang*, Tiantian Mi*, Weiye Si, Qipeng Guo, Siyuan Feng, Pengfei Liu†

    ACL 2026 (main)

    [Paper][Code][🤗 Dataset][🤗 Model (3B)][🤗 Model (7B)][🤗 Benchmark]

  • InnovatorBench: Evaluating Agents’ Ability to Conduct Innovative LLM Research

    Yunze Wu, Dayuan Fu, Weiye Si, Zhen Huang, Mohan Jiang, Keyu Li, Shijie Xia, Jie Sun, Tianze Xu, Xiangkun Hu, Pengrui Lu, Xiaojie Cai, Lyumanshan Ye, Wenhong Zhu, Yang Xiao, Pengfei Liu†

    ICLR 2026

    [Paper][Code][🤗 Dataset][OpenReview]

  • LIMO: Less is More for Reasoning

    Yixin Ye*, Zhen Huang*, Yang Xiao, Ethan Chern, Shijie Xia, Pengfei Liu†

    COLM 2025

    [Paper][Code][Model][🤗 Datasets][Featured by AK][机器之心][Talk (Chinese)]

  • OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI

    Zhen Huang, Zengzhi Wang, Shijie Xia, Xuefeng Li, Haoyang Zou, Ruijie Xu, Run-Ze Fan, Lyumanshan Ye, Ethan Chern, Yixin Ye, Yikai Zhang, Yuqing Yang, Ting Wu, Binjie Wang, Shichao Sun, Yang Xiao, Yiyuan Li, Fan Zhou, Steffi Chern, Yiwei Qin, Yan Ma, Jiadi Su, Yixiu Liu, Yuxiang Zheng, Shaoting Zhang†, Dahua Lin†, Yu Qiao†, Pengfei Liu†

    NeurIPS 2024

    [Paper][Code][Homepage][🤗 Datasets][ 🤗 Competition][Featured by AK][机器之心][量子位]

📖 Educations

  • 2025.09 - 2030.06 (Expected), Ph.D. in Computer Science and Technology, Fudan University, Shanghai, China
    • Research focus: Large Language Models
  • 2021.09 - 2025.07, B.Eng. in Software Engineering, Soochow University, Suzhou, China
    • GPA: 4.0/4.0, Ranking: 1/95
    • I conduct research on data mining and recommender systems under the supervision of Pengpeng Zhao during my time at ADALab, which is founded by Prof. Xiaofang Zhou (the current head of the Computer Science department at HKUST).

🌐 Services

  • Reviewer: NeurIPS 2025, ICLR 2026, ICML 2026

🥥 Misc

  • ⚽️ I’m a passionate football enthusiast. I’m a devoted Chelsea FC supporter, drawn to the club’s legendary spirit—a testament to resilience, determination, and never giving up. Beyond the club itself, I’m an ardent admirer of José Mourinho, whose distinctive personality and tactical genius (counter-attacking) have left an indelible mark on football.