About Me

Hello! I am Kunlun Zhu, a graduate student at the University of Illinois Urbana-Champaign, I am currently co-advised by Prof. Jiaxuan You at Ulab and Prof. Heng Ji at the BlenderLab. Prior to this, I spent two years as a Research Assistant in the Natural Language Processing group at Tsinghua University and as an Algorithm Engineer at ModelBest Inc., working under the guidance of Prof. Zhiyuan Liu. I’m also proud to be a member of OpenBMB.

I am currently collaborating with Prof. James Zou at Stanford University and was a visiting student there during the summer of 2025.

My research journey has been diverse and enriching. I had the opportunity to work as a Research Assistant for 6 months at the Mila Quebec AI Institute’s Graph Team, collaborating with Prof. Jian Tang. Additionally, I spent a year as a research intern at Carnegie Mellon University’s Robotics Institute, working alongside Prof. Katia Sycara. More details about my experience can be found at CV.

I’m always eager to expand my research horizons! If you’re a master’s or undergraduate student seeking research experience, or a PhD student interested in collaboration, I’d be delighted to hear from you. Feel free to reach out to me at kunlunz2@illinois.edu to explore potential research opportunities together.

🎆 News

  • Sep 2025 – Our paper on AI Scientist Safety has been officially accepted at Nature Communications.
  • Aug 2025 – Our paper SafeScientist has been accepted at the EMNLP 2025 Main Conference.
  • Jun 2025 – Gave an invited talk on OpenManus Agent at the AMD Annual AI Conference.

Research Interests

My research interests are centered around large language models (LLMs) and their applications. I’m particularly fascinated by:

  • Post-training for agent: Reinforcement Learning, Agent tuning
  • Agentic System including:
    • Tool learning and Planning
    • Embodied Agents
    • Multi-agent systems
  • Agents for scientific research

I’m excited about pushing the boundaries of what’s possible with LLMs and exploring how they can be leveraged to solve complex problems across various domains.

Selected Publications & Preprints

  1. EMNLP Demo 2025. H. Yu, K. Xuan, F. Li, K. Zhu, Z. Lei, J. Zhang, Z. Qi, J. You. “TinyScientist: A Lightweight Framework for Building Research Agents.” Code, 2025.

  2. EMNLP 2025 Main. K. Zhu, J. Zhang, Z. Qi, N. Shang, Z. Liu, P. Han, Y. Su, H. Yu, J. You. “SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents.” arXiv:2505.23559, 2025.

  3. Preprint 2025. B. Liu, X. Li, J. Zhang, J. Wang, T. He, S. Hong, H. Liu, S. Zhang, K. Song, K. Zhu, Y. Cheng, et al. “Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems.” arXiv:2504.01990, 2025.

  4. ACL 2025 Main. K. Zhu, H. Du, Z. Hong, X. Yang, S. Guo, Z. Wang, Z. Wang, C. Qian, X. Tang, H. Ji, J. You. “MultiAgentBench: Evaluating the Collaboration and Competition of LLM Agents.” arXiv:2503.01935, 2025.

  5. ICML 2025. H. Yu, Z. Hong, Z. Cheng, K. Zhu, K. Xuan, J. Yao, T. Feng, J. You. “ResearchTown: Simulator of Human Research Community.” arXiv:2412.17767, 2024.

  6. ACL 2025 Main. K. Zhu, Y. Luo, D. Xu, R. Wang, S. Yu, S. Wang, Y. Yan, Z. Liu, X. Han, Z. Liu, M. Sun. “RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework.” arXiv:2408.01262, 2024.

  7. Nature Communications (Accepted) 2024. X. Tang, Q. Jin, K. Zhu, T. Yuan, Y. Zhang*, W. Zhou, M. Qu, Y. Zhao, J. Tang, Z. Zhang, A. Cohan, Z. Lu, M. Gerstein. “Prioritizing Safeguarding Over Autonomy: Risks of LLM Agents for Science.” arXiv:2402.04247, 2024.

  8. ICLR 2025. C. Qian, Z. Xie, Y. Wang, W. Liu, K. Zhu*, Y. Dang, Z. Du, W. Chen, C. Yang, Z. Liu, M. Sun. “Scaling Large-Language-Model-based Multi-Agent Collaboration.” arXiv:2406.07155, 2024.

  9. TMLR Survey 2024. T. Feng, K. Zhu, C. Jin, J. Liu, H. Tu, Z. Cheng, G. Lin, J. You. “How Far Are We From AGI.” arXiv:2405.10313, 2024.

  10. ACL 2023 Main. Y. Qin, Z. Cai, D. Jin, L. Yan, S. Liang, K. Zhu, Y. Lin, X. Han, N. Ding, H. Wang, et al. “WebCPM: Interactive Web Search for Chinese Long-form Question Answering.” In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 8968–8988, 2023. 50+ citations.

  11. ICLR 2024 Spotlight. Y. Qin, S. Liang, Y. Ye, K. Zhu, L. Yan, Y. Lu, Y. Lin, X. Cong, et al. “ToolLLM: Facilitating Large Language Models to Master 16000+ Real-World APIs.” arXiv:2307.16789, 2023. 500+ citations.

  12. TMLR 2024. S. Liang, R. Tian, K. Zhu, Y. Qin, H. Wang, X. Cong, Z. Liu, X. Liu, M. Sun. “Exploring Format Consistency for Instruction Tuning.” *Transactions on Machine Learning Research, 2023.

  13. Preprint 2023. K. Zhu, S. Liang, X. Han, Z. Zheng, G. Zeng, Z. Liu, M. Sun. “QASnowball: An Iterative Bootstrapping Framework for High-Quality Question-Answering Data Generation.” arXiv:2309.10326, 2023.

  14. ACM Computing Surveys 2023. Y. Qin, S. Hu, Y. Lin, W. Chen, N. Ding, G. Cui, Z. Zeng, Y. Huang, C. Xiao, C. Han, et al. “Tool Learning with Foundation Models.” arXiv:2304.08354, 2023. 200+ citations.

Services

  • ICLR 2025: Reviewer
  • NeurIPS 2025: Main Conference Reviewer
  • ICLR 2024: Reviewer for workshops on “How far are we from AGI” and “LLM agent”
  • ACL 2024: Reviewer for the “Word Play” workshop
  • ACL ARR 2024: June Reviewer

Talk

  • Introduction to XAgent: The State of the art agent system: Alibaba Yunxi Agent Workshop 2023