@article{evaluatinginteractivereasoninginlargelan,
  title = {Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games},
  author = {Mingyuan Fan and Weiguang Han and Daixin Wang and Cen Chen and Zhiqiang Zhang and Jun Zhou},
  year = {2026},
  eprint = {2606.00103},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.00103},
}