Shaokun Zhang

Publications

2026

• Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning
  Shaokun Zhang, Yi Dong, Jieyu Zhang, Jan Kautz, Bryan Catanzaro, Andrew Tao, Qingyun Wu, Zhiding Yu, Guilin Liu
  International Conference on Learning Representations (ICLR), 2026
  (paper, code)

2025

• Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
  Shaokun Zhang*, Ming Yin*, Jieyu Zhang, Jiale Liu, Zhiguang Han, Jingyang Zhang, Beibin Li, Chi Wang, Huazheng Wang, Yiran Chen, Qingyun Wu
  International Conference on Machine Learning (ICML), 2025 (Spotlight Presentation, 313/12108=2.6%)
  (paper, code)
• BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
  Dujian Ding, Ankur Mallick, Shaokun Zhang, Chi Wang, Daniel Madrigal, Mirian Del Carmen Hipolito Garcia, Menglin Xia, Laks V. S. Lakshmanan, Qingyun Wu, Victor Rühle
  International Conference on Machine Learning (ICML), 2025
  (paper, code)
• A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence
  ..., Shaokun Zhang, et al.
  Transactions on Machine Learning Research (TMLR)
  (paper, code)
• EcoAct: Economic Agent Determines When to Register What Action
  Shaokun Zhang, Jieyu Zhang, Dujian Ding, Mirian Hipolito Garcia, Ankur Mallick, Daniel Madrigal, Menglin Xia, Victor Ruhle, Qingyun Wu, Chi Wang
  International Conference on Learning Representations (ICLR) Workshop, 2025
  (paper)
• Adaptive In-conversation Team Building for Language Model Agents
  Linxin Song, Jiale Liu*, Jieyu Zhang, Shaokun Zhang, Ao Luo, Shijian Wang, Qingyun Wu, Chi Wang
  Conference on Language Modeling (COLM) Workshop, 2025
  (paper, code)
• Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
  ..., Shaokun Zhang, et al.
  arXiv Preprint
  (paper, code)

2024

• Offline Training of Language Model Agents with Functions as Learnable Weights
  Shaokun Zhang*, Jieyu Zhang*, Jiale Liu, Linxin Song, Chi Wang, Ranjay Krishna, Qingyun Wu
  International Conference on Machine Learning (ICML), 2024 (Forbes Coverage)
  (paper, code)
• Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints
  Xiaobo Xia, Jiale Liu, Shaokun Zhang, Qingyun Wu, Hongxin Wei, Tongliang Liu
  International Conference on Machine Learning (ICML), 2024 (Spotlight Presentation, 355/9473=3.74%, collected by OpenAI PaperBench)
  (paper, code)
• IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
  Shaokun Zhang*, Xiaobo Xia*, Zhaoqing Wang, Lin-Hao Chen, Jiale Liu, Qingyun Wu, Tongliang Liu
  International Conference on Learning Representations (ICLR), 2024
  (paper, code)
• StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
  Yiran Wu, Tianwei Yue, Shaokun Zhang, Chi Wang, Qingyun Wu
  Conference on Language Modeling (COLM), 2024
  (paper, code)
• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
  Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, Chi Wang
  International Conference on Learning Representations (ICLR) Workshop, 2024 (Best Paper); Conference on Language Modeling (COLM), 2024
  (paper, code)
• Fair Online Influence Maximization
  Xiangqi Wang, Shaokun Zhang, Jose Efraim Aguilar Escamilla, Qingyun Wu, Xiangliang Zhang, Jian Kang, Huazheng Wang
  Transactions on Machine Learning Research (TMLR)
  (paper, code)
• An Empirical Study on Challenging Math Problem Solving with GPT-4
  Yiran Wu, Feiran Jia, Shaokun Zhang, Hangyu Li, Erkang Zhu, Yue Wang, Yin Tat Lee, Richard Peng, Qingyun Wu, Chi Wang
  International Conference on Learning Representations (ICLR) Workshop, 2024
  (paper, code)

Before 2023

• Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives
  Shaokun Zhang, Feiran Jia, Chi Wang, Qingyun Wu
  International Conference on Learning Representations (ICLR), 2023 (Oral Presentation, 91/4955=2.39%)
  (paper, code)
• HyperTime: Hyperparameter Optimization for Combating Temporal Distribution Shifts
  Shaokun Zhang, Yiran Wu, Zhonghua Zheng, Qingyun Wu, Chi Wang
  ACM International Conference on Multimedia (ACM MM), 2023
  (paper, code)
• You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
  Shaokun Zhang, Xiawu Zheng, Chenyi Yang, Yuchao Li, Yan Wang, Fei Chao, Mengdi Wang, Shen Li, Jun Yang, Rongrong Ji
  Neurocomputing
  (paper, code)
• Efficient Neural Architecture Search via Dynamic Distribution Pruning
  Xiawu Zheng, Chenyi Yang, Shaokun Zhang, Yan Wang, Baochang Zhang, Yongjian Wu, Yunsheng Wu, Ling Shao, Rongrong Ji
  International Journal of Computer Vision (IJCV)
  (paper, code)

(*equal contribution)

Open Source Projects

• AutoGen : Creator. 40k+ stars, Open100: Top 100 Open Source Achievements
• FLAML : Maintainer. 3.3k+ stars, 1 million+ downloads

Experience

• NVIDIA (Santa Clara) : Research Intern, Feb 2025 - Dec 2025. LLMs Post-training.
• Microsoft Research (Redmond) : Research Intern, Jun 2024 - Sep 2024. Language Agent.