@article{simmerbenchmarkinglatentfailuresinllmexe,
  title = {SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model},
  author = {Xiaoxin Lu and Ranran Haoran Zhang and Rui Zhang},
  year = {2026},
  eprint = {2606.14574},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.14574},
}