@misc{zheng2026actfirst,
  title = {{Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics}},
  author = {Zubin Zheng and Jiahao Wu and Shaofeng Zhang and Zhirui Zhang and Yew-Soon Ong and Shengcai Liu},
  year = {2026},
  eprint = {2609.36608},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.36608},
  url = {https://arxiv.org/abs/2609.36608}
}
