The work, in print.

@misc{protocolbench,
  title = {ProtocolBench: Which LLM MultiAgent Protocol to Choose?},
  author = {Hongyi Du and Jiaqi Su and Jisen Li and Lijie Ding and Yingxuan Yang and Peixuan Han and Xiangru Tang and Kunlun Zhu and Jiaxuan You},
  eprint = {2510.17149},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.17149}
}

@misc{psibench,
  title = {Ψ-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues},
  author = {Peixuan Han and Hongyi Du and Jiayu Liu and Yihang Sun and Jiaxuan You},
  eprint = {2606.02754},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.02754}
}

@misc{multiagentbench,
  title = {MultiAgentBench: Evaluating the Collaboration and Competition of LLM Agents},
  author = {Kunlun Zhu and Hongyi Du and Zhaochen Hong and Xiaocheng Yang and Shuyi Guo and Zhe Wang and Zhenhailong Wang and Cheng Qian and Xiangru Tang and Heng Ji and Jiaxuan You},
  eprint = {2503.01935},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.01935}
}

@misc{modelingagent,
  title = {ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges},
  author = {Cheng Qian and Hongyi Du and Hongru Wang and Xiusi Chen and Yuji Zhang and Avirup Sil and Chengxiang Zhai and Kathleen McKeown and Heng Ji},
  eprint = {2505.15068},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.15068}
}

@misc{escapebench,
  title = {EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents},
  author = {Cheng Qian and Peixuan Han and Qinyu Luo and Bingxiang He and Xiusi Chen and Yuji Zhang and Hongyi Du and Jiarui Yao and Xiaocheng Yang and Denghui Zhang and Yunzhu Li and Heng Ji},
  eprint = {2412.13549},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.13549}
}