Hi! Welcome to Dayuan Fu’s homepage!

I am Dayuan Fu, a graduate student at PRIS-NLP Group at Beijing University of Posts and Telecommunications (BUPT), supervised by Prof. Weiran Xu. I’m visiting GAIR now, and I visited TsinghuaC3I group from 2022.10 to 2024.8.

My research interests primarily focus on LLM Agents automation including both expanding the range of agent applications via agent itself and using agents to discover new Nobel Prize level laws/rules. I believe combining search with powerful LLM is the way to AGI.

Now, I’m working on the following research topics:

Coding Agent: Training long horizon coding agents for SWE and research automation.
Evolve with Search Harness: Developing (tree) search harnesses for novel insight discovery. Including improve the search efficiency and node expand quality.
AI for AI system: Using AI to speedup AI research and development.

I have published several papers at prominent NLP conferences, including ICLR, ICML, EMNLP, CIKM, and NAACL.

🔥 News

2026-05: 🎉🎉 One papers has been accepted by ICML 2026 Spotlight!
2026-01: 🎉🎉 Two papers have been accepted by ICLR 2026!
2025-09: 🎉🎉 One paper has been accepted by EMNLP 2025!
2025-01: 🎉🎉 Two papers have been accepted by ICLR 2025!
2024-09: 🎉🎉 Two papers have been accepted by EMNLP 2024!

📝 Selected Publication

(* denotes equal contributions)

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]

daVinci-Env: Open SWE Environment Synthesis at Scale
Dayuan Fu, Shenyu Wu, Yunze Wu, Zerui Peng, Yaxing Huang, Jie Sun, Ji Zeng, Mohan Jiang, Lin Zhang, Yukun Li, Jiarui Hu, Liming Liu, Jinlong Hou, Pengfei Liu
working in progress [paper] [dataset] [code]

daVinci-Dev: Agent-native Mid-training for Software Engineering
Ji Zeng, Dayuan Fu, Tiantian Mi, Zhuang Yumin, 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 spotlight [paper] [dataset] [code]

daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently
Mohan Jiang, Dayuan Fu, Junhao Shi, Ji Zeng, Weiye Si, Keyu Li, Xuefeng Li, Yang Xiao, Wenjie Li, Dequan Wang, Pengfei Liu
working in progress [paper] [dataset] [code]

AgentRefine: Enhancing Agent Generalization through Refinement Tuning
Dayuan Fu, Keqing He, Yejie Wang, Wentao Hong, Zhuoma Gongque, Weihao Zeng, Wei Wang, Jingang Wang, Xunliang Cai, Weiran Xu
ICLR 2025 [paper] [website] [code]

DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments
Yuxiang Zheng*, Dayuan Fu*, Xiangkun Hu*, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, Pengfei Liu
EMNLP 2025 Main [paper] [code] [机器之心]

MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making
Dayuan Fu, Biqing Qi, Yihuai Gao, Che Jiang, Guanting Dong, Bowen Zhou
EMNLP 2024 Main [paper]

PreAct: Prediction Enhances Agent’s Planning Ability

Dayuan Fu, Jianzhao Huang, Siyuan Lu, Guanting Dong, Yejie Wang, Keqing He, Weiran Xu
Coling 2025 [paper] [code]

How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data
Yejie Wang*, Keqing He*, Dayuan Fu*, Zhuoma Gongque, Heyang Xu, Yanxu Chen, Zhexu Wang, Yujia Fu, Guanting Dong, Muxi Diao, Jingang Wang, Mengdi Zhang, Xunliang Cai, Weiran Xu
EMNLP 2024 Main [paper] [code]

CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery

Xiaoshuai Song, Muxi Diao, Guanting Dong, Zhengyang Wang, Yujia Fu, Runqi Qiao, Zhexu Wang, Dayuan Fu, Huangxuan Wu, Bin Liang, Weihao Zeng, Yejie Wang, Zhuoma GongQue, Jianing Yu, Qiuna Tan, Weiran Xu
ICLR 2025 [paper] [website] [code] [dataset] [blog]

总访问量次
总访客数人次