CV

Kaiwen Xiong (熊恺文)

x_kevin@sjtu.edu.cn

Education

• B.S. in Automation, Shanghai Jiao Tong University, 2023 – 2027 (expected)

Work experience

• Research Assistant Feb 2025 – Present
  • Institute: AIMING Lab, UNC-Chapel Hill
  • Research Topic: placeholder
  • Advisor: Huaxiu Yao
• Algorithms Research Intern Jun 2025 – Sep 2025
  • Institute: Manycore Research Institute, Manycore Tech.
  • Research Topic: A Spatial Language Model (SpatialLM) for interactive 3D scene generation
  • Leader: Zihan Zhou
• Research Assistant Oct 2023 – Oct 2024
  • Institute: The State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University
  • Research Topic: Autonomous observation and control of unmanned aerial vehicles
  • Advisor: Wei Dong

Publications

• ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents

  Kaiwen Xiong, Haonian Ji, Shi Qiu, Zeyu Zheng, Cihang Xie, Xinyu Ye, Huaxiu Yao, "ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents," 2026. [Online]. Available: https://arxiv.org/abs/2606.31174

• ClawArena: Benchmarking AI Agents in Evolving Information Environments

  Haonian Ji, Kaiwen Xiong, Siwei Han, Peng Xia, Shi Qiu, Yiyang Zhou, Jiaqi Liu, Jinlong Li, Bingzhou Li, Zeyu Zheng, Cihang Xie, Huaxiu Yao, "ClawArena: Benchmarking AI Agents in Evolving Information Environments," 2026. [Online]. Available: https://arxiv.org/abs/2604.04202

• MetaClaw: Just Talk – An Agent That Meta-Learns and Evolves in the Wild

  Peng Xia, Jianwen Chen, Xinyu Yang, Haoqin Tu, Jiaqi Liu, Kaiwen Xiong, Siwei Han, Shi Qiu, Haonian Ji, Yuyin Zhou, Zeyu Zheng, Cihang Xie, Huaxiu Yao, "MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild," 2026. [Online]. Available: https://arxiv.org/abs/2603.17187

• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails

  Siwei Han, Kaiwen Xiong, Jiaqi Liu, Xinyu Ye, Yaofeng Su, Wenbo Duan, Xinyuan Liu, Cihang Xie, Mohit Bansal, Mingyu Ding, Linjun Zhang, Huaxiu Yao, "Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails," 2026. [Online]. Available: https://arxiv.org/abs/2510.04860v2

• Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning

  Jiaqi Liu, Kaiwen Xiong, Peng Xia, Yiyang Zhou, Haonian Ji, Lu Feng, Siwei Han, Mingyu Ding, Huaxiu Yao, "Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning," in Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026. Oral presentation.

• An Adaptive Sliding Window Estimator for Positioning of Unmanned Aerial Vehicle Using a Single Anchor

  Kaiwen Xiong, Sijia Chen, Wei Dong, "An Adaptive Sliding Window Estimator for Positioning of Uncrewed Aerial Vehicle Using a Single Anchor," in IEEE Sensors Journal, vol. 25, no. 16, pp. 30799-30809, 15 Aug.15, 2025, doi: 10.1109/JSEN.2025.3582282.

Skills

• Programming: Python, C/C++, MATLAB, \(\LaTeX\)
• Tools: Claude Code, Openclaw, Adobe Photoshop