About Me

Hello! I am Kunlun Zhu, a Computer Science Ph.D. student at the University of Illinois Urbana-Champaign (UIUC), advised by Prof. Heng Ji at BlenderLab. I completed my M.S. in Computer Science at UIUC, advised by Prof. Jiaxuan You and Prof. Heng Ji. I am currently a Research Intern at Apodex AI (since June 2026), working on Agentic AI and Agents for Science.

I also collaborate closely with Prof. James Zou at Stanford University, where I was a visiting student in 2025. Earlier, 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 with Prof. Zhiyuan Liu, and I am a proud member of OpenBMB. Before that, I was a Research Assistant in the Graph Team at Mila – Quebec AI Institute with Prof. Jian Tang, and a research intern at Carnegie Mellon University's Robotics Institute with Prof. Katia Sycara.

🎆 News

• Jul 2026Started as a Research Intern at Apodex AI, working on Agentic AI and Agents for Science.
• May 2026ProtocolBench (Which LLM Multi-Agent Protocol to Choose?) was accepted at ICML 2026.
• Feb 2026SWE-Bench Mobile was accepted at KDD 2026.
• Sep 2025Our paper on AI Scientist Safety was officially published in Nature Communications.
• Aug 2025SafeScientist was accepted at the EMNLP 2025 Main Conference.
• Jun 2025Gave an invited talk on the OpenManus agent at the AMD Advancing AI 2025 conference.

🧭 Research Interests

My research builds and studies agentic systems powered by large language models, with the long-term goal of AI that can reliably reason, collaborate, and accelerate scientific discovery. My current focus areas:

📚 Selected Publications & Preprints

(bold = me  ·  * = equal contribution  ·  † = corresponding author). A full list is on my Google Scholar.

Preprint · 2025 · 90+ citations AgentDebug: Where LLM Agents Fail and How They Can Learn From Failures

K. Zhu, Z. Liu, B. Li, M. Tian, Y. Yang, J. Zhang, P. Han, Q. Xie, F. Cui, W. Zhang, X. Ma, X. Yu, G. Ramesh, Y. Su, J. Wu, Z. Liu, P. Lu, J. Zou, J. You

arXiv

EMNLP 2025 Main SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents

K. Zhu, J. Zhang, Z. Qi, N. Shang, Z. Liu, P. Han, Y. Su, H. Yu, J. You

arXiv

ICML 2026 Which LLM Multi-Agent Protocol to Choose? (ProtocolBench)

H. Du, J. Su, J. Li, L. Ding, Y. Yang, P. Han, X. Tang, K. Zhu^†, J. You^†

arXiv

KDD 2026 SWE-Bench Mobile: Can LLM Agents Develop Industry-Level Mobile Applications?

M. Tian, Z. Wang, B. Yang, Z. Tang, K. Zhu, H. Dong, H. Li, X. Xie, G. Wang, et al.

arXiv

ACL 2025 Main · 220+ citations MultiAgentBench: Evaluating the Collaboration and Competition of LLM Agents

K. Zhu, H. Du, Z. Hong, X. Yang, S. Guo, Z. Wang, Z. Wang, C. Qian, X. Tang, H. Ji, J. You

arXiv Code

EMNLP 2025 Demo TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents

H. Yu, K. Xuan, F. Li, K. Zhu, Z. Lei, J. Zhang, Z. Qi, K. Richardson, J. You

arXiv Code

Preprint · 2025 · 250+ citations Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

B. Liu, X. Li, J. Zhang, J. Wang, T. He, S. Hong, H. Liu, S. Zhang, K. Song, K. Zhu, Y. Cheng, et al.

arXiv

ICML 2025 ResearchTown: Simulator of Human Research Community

H. Yu*, Z. Hong*, Z. Cheng*, K. Zhu*, K. Xuan, J. Yao, T. Feng, J. You

arXiv Code

ACL 2025 Main RAGEval: Scenario-Specific RAG Evaluation Dataset Generation Framework

K. Zhu, Y. Luo, D. Xu, R. Wang, S. Yu, S. Wang, Y. Yan, Z. Liu, X. Han, Z. Liu, M. Sun

arXiv

Nature Communications 2024 · 140+ citations Prioritizing Safeguarding Over Autonomy: Risks of LLM Agents for Science

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

arXiv

ICLR 2025 · 350+ citations Scaling Large-Language-Model-based Multi-Agent Collaboration

C. Qian, Z. Xie, Y. Wang, W. Liu, K. Zhu*, Y. Dang, Z. Du, W. Chen, C. Yang, Z. Liu, M. Sun

arXiv

TMLR 2024 · Survey How Far Are We From AGI: Are LLMs All We Need?

T. Feng*, K. Zhu*, C. Jin*, J. Liu*, H. Tu, Z. Cheng, G. Lin, J. You

arXiv

ICLR 2024 Spotlight · 2200+ citations ToolLLM: Facilitating LLMs to Master 16000+ Real-World APIs

Y. Qin, S. Liang, Y. Ye, K. Zhu, L. Yan, Y. Lu, Y. Lin, X. Cong, et al.

arXiv

ACL 2023 Main · 120+ citations WebCPM: Interactive Web Search for Chinese Long-form Question Answering

Y. Qin, Z. Cai, D. Jin, L. Yan, S. Liang, K. Zhu, Y. Lin, X. Han, N. Ding, H. Wang, et al.

arXiv

TMLR 2024 Exploring Format Consistency for Instruction Tuning

S. Liang*, R. Tian*, K. Zhu*, Y. Qin, H. Wang, X. Cong, Z. Liu, X. Liu, M. Sun

arXiv

ACM Computing Surveys 2024 · 700+ citations Tool Learning with Foundation Models

Y. Qin, S. Hu, Y. Lin, W. Chen, N. Ding, G. Cui, Z. Zeng, Y. Huang, C. Xiao, C. Han, et al.

arXiv

Preprint · 2023 QASnowball: An Iterative Bootstrapping Framework for High-Quality QA Data Generation

K. Zhu, S. Liang, X. Han, Z. Zheng, G. Zeng, Z. Liu, M. Sun

arXiv

🧪 Other Recent Work

• bioRxiv 2026 — Eubiota: Modular Agentic AI for Autonomous Discovery in the Gut Microbiome. P. Lu, Y. Gao, ..., K. Zhu, et al.
• Preprint 2026 — BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery.
• Preprint 2026 — Advancing Creative Physical Intelligence in Large Multimodal Models.
• Preprint 2026 — Augmenting Interface Usability Heuristics for Reliable Computer-Use Agents.
• Open Source — OpenManus & OpenManus-RL: an open-source framework for building general AI agents (50k+ ★).

🌱 Internship Alumni

I've had the privilege of mentoring these talented students during their research internships:

• Hongyi DuUIUC Undergrad → UIUC MSCS
• Jiaqi SuSJTU Undergrad → NTU RA
• Jiaxun ZhangUIUC Undergrad → UCSD PhD
• Jisen LiUIUC Undergrad → Together AI
• Muxin TianUToronto Undergrad → Harvard RA
• Weijia ZhangUIUC Undergrad → Yale MSCS
• Ziheng QiUIUC Undergrad → Harvard MS

🛠️ Services & Talks

• Reviewer — ICML 2025, ICLR 2024/2025, NeurIPS 2024/2025, ACL ARR 2024, and associated workshops.
• Invited Speaker — AMD Advancing AI 2025, "Developing AI Agents with AMD GPUs"; Alibaba Yunxi Agent Workshop 2024 ("XAgent").
• Teaching Assistant — CS107 Data Science Discovery, UIUC (Fall 2024, Spring 2025, Fall 2025).
• Community — Founding organizer of the "Foundation Agents" organization; member of OpenBMB.