@article{collabovercookedbenchmarkingandevaluatin,
  title = {Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents},
  author = {Haochen Sun and Shuwen Zhang and Lujie Niu and Lei Ren and Hao Xu and Hao Fu and Fangkun Zhao and Caixia Yuan and Xiaojie Wang},
  year = {2025},
  eprint = {2502.20073},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.20073v2},
}