@article{evaluatinglargelanguagemodelswithruntime,
  title = {Reasoning Runtime Behavior of a Program with LLM: How Far Are We?},
  author = {Junkai Chen and Zhiyuan Pan and Xing Hu and Zhenhao Li and Ge Li and Xin Xia},
  year = {2024},
  eprint = {2403.16437},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.16437v3},
}