@article{mitigatingthinkanswermismatchinllmreason,
  title = {Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting},
  author = {Si Shen and Peijun Shen and Wenhua Zhao and Danhao Zhu},
  year = {2025},
  eprint = {2508.05928},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.05928},
}